Imagry · Machine Learning Engineer
Updated · 2026-10-02

Imagry Machine Learning Engineer
Interview Questions & Guide 2026

THE 60-SECOND BRIEF

A Machine Learning Engineer at Imagry plays a critical role in pioneering the future of autonomous driving. Unlike traditional autonomous vehicle companies that rely heavily on expensive, HD-mapping solutions, Imagry focuses on a mapless, real-time vision-based approach. This means the machine learning models you build, train, and deploy are directly responsible for the vehicle's real-time perception, localization, and decision-making capabilities. You will work on safety-critical systems where low latency, high efficiency, and robustness are absolute necessities.

Treat capacity estimation as a conversion skill rather than a table to memorise: turn a user count and an action rate into requests per second and bytes per day, then name the component that number breaks first. The figure only matters if it changes the design.

Imagry candidates report 6 rounds · ≈ 4-6 weeks. The stages below are what candidates describe, not a published process.

Choose indexes from the query's access pathBound every outbound call with a timeoutDetect concurrent edits instead of losing writes

41 min read

Browse Machine Learning Engineer questions

See the practice prompts

15Practice promptsAcross five skill areas
3With worked solutionsIncluded in the practice prompts

A Machine Learning Engineer at Imagry plays a critical role in pioneering the future of autonomous driving. Unlike traditional autonomous vehicle companies that rely heavily on expensive, HD-mapping solutions, Imagry focuses on a mapless, real-time vision-based approach. This means the machine learning models you build, train, and deploy are directly responsible for the vehicle's real-time perception, localization, and decision-making capabilities. You will work on safety-critical systems where low latency, high efficiency, and robustness are absolute necessities.

The impact of this role is immediate and profound. Your work directly influences how safely and smoothly a vehicle navigates complex, unmapped urban environments. This requires solving highly challenging problems at the intersection of deep learning, computer vision, and low-level systems engineering. You will be tasked with translating cutting-edge academic research into highly optimized, production-grade code that can run efficiently on edge devices.

To succeed in this position, you must possess a rare blend of deep theoretical knowledge and hands-on software engineering discipline. values engineers who understand the underlying mathematical foundations of machine learning and can implement these concepts from scratch using and. It is an environment designed for those who thrive on solving open-ended physical-world challenges and want to see their algorithms running on real vehicles.

01

Online Coding Assessment

reported

Most of the time lost in this format is not lost to thinking. It goes to a standard-library call you half-remember, an off-by-one in a loop bound, and a debugging loop that mutates code at random until something passes. When output is wrong, stop re-reading the whole function: take the smallest input that reproduces it and walk the state through by hand, printing intermediates if the environment allows. Guessing at a fix without a failing case you understand is how a five-minute bug becomes twenty, and the clock does not pause while you do it.

What to demonstrate

  • Whether you reach the right structure without a detour, and can write it from memory rather than only recall that one exists
  • Whether overflow is considered where the language has fixed-width integers, since a signed 32-bit value stops at 2,147,483,647 and then wraps in Java, is undefined behaviour in C++, and does not arise in Python, whose integers grow instead
  • Whether recursion depth is treated as a constraint on large inputs, given that CPython's default limit is 1000 frames and a deep recursion can exhaust the stack in any language where an iterative version would not
  • Whether a failing case is isolated and explained before any edit is made to the code

How to prepare

  • From an empty file and with no references open, implement the pieces you lean on most: a heap push and pop, an iterative DFS with an explicit stack, and a binary search whose midpoint is written lo + (hi - lo) / 2, which avoids the overflow that (lo + hi) / 2 can hit in a fixed-width integer type
  • Time yourself on the ten library calls you look up most, such as sorting with a custom comparator, splitting and joining strings, and finding the next key at or above a value in an ordered map, until the lookup is gone
  • Take a solution you know is broken and, before touching it, write one sentence naming the input, the expected value and the actual value. Repeat until you do it without deciding to.
PracHub interview research ↗
02

Deep-Dive Technical Interviews

reported

Most of the time lost in this format is not lost to thinking. It goes to a standard-library call you half-remember, an off-by-one in a loop bound, and a debugging loop that mutates code at random until something passes. When output is wrong, stop re-reading the whole function: take the smallest input that reproduces it and walk the state through by hand, printing intermediates if the environment allows. Guessing at a fix without a failing case you understand is how a five-minute bug becomes twenty, and the clock does not pause while you do it.

What to demonstrate

  • Whether you reach the right structure without a detour, and can write it from memory rather than only recall that one exists
  • Whether overflow is considered where the language has fixed-width integers, since a signed 32-bit value stops at 2,147,483,647 and then wraps in Java, is undefined behaviour in C++, and does not arise in Python, whose integers grow instead
  • Whether recursion depth is treated as a constraint on large inputs, given that CPython's default limit is 1000 frames and a deep recursion can exhaust the stack in any language where an iterative version would not
  • Whether a failing case is isolated and explained before any edit is made to the code

How to prepare

  • From an empty file and with no references open, implement the pieces you lean on most: a heap push and pop, an iterative DFS with an explicit stack, and a binary search whose midpoint is written lo + (hi - lo) / 2, which avoids the overflow that (lo + hi) / 2 can hit in a fixed-width integer type
  • Time yourself on the ten library calls you look up most, such as sorting with a custom comparator, splitting and joining strings, and finding the next key at or above a value in an ordered map, until the lookup is gone
  • Take a solution you know is broken and, before touching it, write one sentence naming the input, the expected value and the actual value. Repeat until you do it without deciding to.
PracHub interview research ↗
03

Practical Implementation Task

reported

You cannot drill a format you do not know, so put the preparation into material that travels. Three pieces of your own work, each rehearsed until you can take a follow-up you did not anticipate, will carry a conversation or a code walkthrough equally well. Specificity is what separates that from filler. A number needs its definition before it means anything: a p99 is over some window and measured at some hop, and a server-side figure excludes the queueing and network time a client would see. The number you cannot qualify is the one to leave out.

What to demonstrate

  • Whether your examples carry detail only someone who did the work would hold, such as what the binding constraint actually was, which alternative you rejected and why it was worse, and what you measured on each side of the change
  • Whether a number survives one follow-up, meaning you can say what it was measured over and whether it moved because of your change or merely alongside it
  • Whether a failure is described with the specific change that followed it, rather than a lesson stated in general terms
  • Whether your part in a team effort is stated accurately, including what other people did

How to prepare

  • Write a page on each of three projects covering the constraint, the option you rejected, the measurement before and after, and what went wrong. Cut any line you cannot take a follow-up on, since you are writing the parts you will be pressed on rather than a summary.
  • Recover the real figures while you still have access: request volume, data size, latency with its percentile and window, team size, timeline. Note where each came from, whether a dashboard, a design document or memory, and mark the estimates so you can say which they are out loud.
  • Take your weakest project story to someone who works in a different area and have them ask why four times in succession. The point where you run out of answer is the part to go and re-read before the round.
PracHub interview research ↗
04

Review of Practical Work

reported

You cannot drill a format you do not know, so put the preparation into material that travels. Three pieces of your own work, each rehearsed until you can take a follow-up you did not anticipate, will carry a conversation or a code walkthrough equally well. Specificity is what separates that from filler. A number needs its definition before it means anything: a p99 is over some window and measured at some hop, and a server-side figure excludes the queueing and network time a client would see. The number you cannot qualify is the one to leave out.

What to demonstrate

  • Whether your examples carry detail only someone who did the work would hold, such as what the binding constraint actually was, which alternative you rejected and why it was worse, and what you measured on each side of the change
  • Whether a number survives one follow-up, meaning you can say what it was measured over and whether it moved because of your change or merely alongside it
  • Whether a failure is described with the specific change that followed it, rather than a lesson stated in general terms
  • Whether your part in a team effort is stated accurately, including what other people did

How to prepare

  • Write a page on each of three projects covering the constraint, the option you rejected, the measurement before and after, and what went wrong. Cut any line you cannot take a follow-up on, since you are writing the parts you will be pressed on rather than a summary.
  • Recover the real figures while you still have access: request volume, data size, latency with its percentile and window, team size, timeline. Note where each came from, whether a dashboard, a design document or memory, and mark the estimates so you can say which they are out loud.
  • Take your weakest project story to someone who works in a different area and have them ask why four times in succession. The point where you run out of answer is the part to go and re-read before the round.
PracHub interview research ↗
05

Discussions with Senior Leaders

reported

You cannot drill a format you do not know, so put the preparation into material that travels. Three pieces of your own work, each rehearsed until you can take a follow-up you did not anticipate, will carry a conversation or a code walkthrough equally well. Specificity is what separates that from filler. A number needs its definition before it means anything: a p99 is over some window and measured at some hop, and a server-side figure excludes the queueing and network time a client would see. The number you cannot qualify is the one to leave out.

What to demonstrate

  • Whether your examples carry detail only someone who did the work would hold, such as what the binding constraint actually was, which alternative you rejected and why it was worse, and what you measured on each side of the change
  • Whether a number survives one follow-up, meaning you can say what it was measured over and whether it moved because of your change or merely alongside it
  • Whether a failure is described with the specific change that followed it, rather than a lesson stated in general terms
  • Whether your part in a team effort is stated accurately, including what other people did

How to prepare

  • Write a page on each of three projects covering the constraint, the option you rejected, the measurement before and after, and what went wrong. Cut any line you cannot take a follow-up on, since you are writing the parts you will be pressed on rather than a summary.
  • Recover the real figures while you still have access: request volume, data size, latency with its percentile and window, team size, timeline. Note where each came from, whether a dashboard, a design document or memory, and mark the estimates so you can say which they are out loud.
  • Take your weakest project story to someone who works in a different area and have them ask why four times in succession. The point where you run out of answer is the part to go and re-read before the round.
PracHub interview research ↗
06

HR Round

reported

Many of these questions are about something that went wrong, and the grading sits mostly in the hours after you knew. Who found out first, whether that was you or an alert or a user, how long it took you to say it out loud, and whether the people who needed the news got it while they could still act on it. Engineers under-tell this part because it feels like confessing. The pattern it is looking for is the opposite: the quiet fix, an incident absorbed without telling anyone, after which nothing changed and the same failure is still available.

What to demonstrate

  • How the problem was found, and whether that route was one you had built or one that happened to you, since a user reporting it first means your instrumentation did not cover that failure
  • Whether time-to-detect and time-to-tell are separate numbers in your account and whether you know both, because a fast fix that nobody heard about until the retro is a different answer from a slow one that was announced immediately
  • Whether the resolution left something durable behind, a check that fires or a default that changed, rather than depending on people remembering to be careful
  • Whether you can say what the failure cost without either inflating it or waving it away

How to prepare

  • Reconstruct one incident you were part of as a timeline with clock times: first bad request, first signal, first person who knew, first message outside the team, mitigation, permanent fix. The gaps between those entries are what gets asked about
  • Look up the configuration of the signal that caught it, including its evaluation window and threshold. An alert defined on a five-minute aggregate cannot fire until the condition holds across that window, which puts a floor under time-to-detect that has nothing to do with how severe the failure was. Be able to say what that floor was and whether anyone had chosen it deliberately
  • Prepare one story where you escalated early and the severity turned out to be smaller than you thought, including what it cost the people you pulled in. Without it, every answer you give about raising alarms is unfalsifiable
PracHub interview research ↗

PracHub editorial advice for the preparation topics above.

01

Choosing an index from the columns a query mentions rather than from how it filters and orders

A composite B-tree index on (a, b, c) can be seeked only as a left prefix: equality on a, then equality on b, then a range or an ordering on c. A query that filters on b alone cannot seek into it at all and at best gets a full scan of the index; a query that filters a and ranges on b gets no benefit from c, because the index is only sorted by c within a fixed (a, b) pair. The practical consequence is that one index per column is close to useless for multi-predicate queries while a single correctly ordered composite index turns a scan into a lookup. The ordering half is what gets missed: if the index cannot satisfy the ORDER BY, the database must read every matching row and sort before the limit can apply, so a LIMIT 20 over a million matching rows still reads a million rows.

02

Assuming an isolation level prevents the anomaly you actually have

Isolation levels are named by the SQL standard but implemented differently, so any claim about one is only true of a named engine. PostgreSQL defaults to READ COMMITTED, where every statement takes a fresh snapshot, so two statements inside one transaction can legitimately disagree about the same row. Its REPEATABLE READ is snapshot isolation: it removes non-repeatable and phantom reads but permits write skew, where two transactions each read a set, each conclude their own write is safe, both commit, and the combined result violates a constraint that no single row expresses. Only SERIALIZABLE closes that, and it closes it by aborting a transaction with a serialization failure (SQLSTATE 40001), which means the guarantee is theoretical unless the application has a retry loop. InnoDB's REPEATABLE READ is a different mechanism again - plain SELECTs read a consistent snapshot while locking reads and writes see the latest committed row - so a read-modify-write inside one transaction can act on a value that the transaction's own earlier SELECT never returned.

03

Issuing one query per row of a result set

Fetch related rows in a single batched query keyed by the ids you already hold, or join them into the original query. A per-row round trip multiplies network latency by the row count, and it looks perfectly fine against the ten rows in your development database.

04

Check-then-act on shared state

Read, decide, write is not safe under concurrency unless the decision and the write are one atomic step: a unique constraint with conflict handling, a compare-and-set, or a row lock held for the whole transaction. Two requests can both pass the existence check before either inserts, which shows up as duplicate rows under load and never in a single-threaded test.

Choose a category, try a prompt, then open its approach, worked solution or follow-up when you need it.

12 technical prompts3 include a worked solution

What is the geometric interpretation of Singular Value Decomposition (…

medium
machine learning fundamentals

What is the geometric interpretation of Singular Value Decomposition (SVD), and how is it used in image processing?

Approach
  1. Pick the metric from the cost of each error type, not from habit.
  2. State the learning problem: the label, the unit of prediction and how the model is used.
  3. Name the simplest model that could work and what would make you move past it.
Follow-up
  • What changes if the classes are heavily imbalanced?
  • How would you know the model is overfitting?

Describe the mechanism of spatial pyramid pooling and why it is benefi…

medium
machine learning fundamentals

Describe the mechanism of spatial pyramid pooling and why it is beneficial for autonomous driving perception tasks.

Approach
  1. Say how you would validate it, and where leakage could enter the split.
  2. Pick the metric from the cost of each error type, not from habit.
  3. State the learning problem: the label, the unit of prediction and how the model is used.
Follow-up
  • What changes if the classes are heavily imbalanced?
  • Where could label leakage enter this setup?

Explain how anchor-free object detection models differ from anchor-bas…

medium
machine learning fundamentals

Explain how anchor-free object detection models differ from anchor-based models in terms of efficiency and accuracy.

Approach
  1. Name the simplest model that could work and what would make you move past it.
  2. Pick the metric from the cost of each error type, not from habit.
  3. Say how you would validate it, and where leakage could enter the split.
Follow-up
  • How would you know the model is overfitting?
  • What changes if the classes are heavily imbalanced?

How do you address the vanishing and exploding gradient problems in ve…

medium
machine learning fundamentals

How do you address the vanishing and exploding gradient problems in very deep neural networks?

Approach
  1. Name the simplest model that could work and what would make you move past it.
  2. Say how you would validate it, and where leakage could enter the split.
  3. Pick the metric from the cost of each error type, not from habit.
Follow-up
  • Where could label leakage enter this setup?
  • What changes if the classes are heavily imbalanced?

How do you optimize memory access patterns in C++ when performing larg…

medium
coding and algorithms

How do you optimize memory access patterns in C++ when performing large-scale matrix multiplications?

Approach
  1. Walk one small example through your approach before writing the whole thing.
  2. Name the brute-force solution and its complexity before improving on it.
  3. State the target complexity and say which constraint rules the naive version out.
Follow-up
  • What is the worst case, and how likely is it on real data?
  • Which test case would catch an off-by-one here?

Implement a custom sliding-window maximum algorithm with optimal time …

medium
coding and algorithms

Implement a custom sliding-window maximum algorithm with optimal time complexity.

Approach
  1. State the target complexity and say which constraint rules the naive version out.
  2. Walk one small example through your approach before writing the whole thing.
  3. Restate the input: its shape, its size, and what is guaranteed about it.
Follow-up
  • What is the worst case, and how likely is it on real data?
  • Which test case would catch an off-by-one here?

Identify the heaviest tenants in a five-minute window under memory pressure

mediumWorked solution
top-kheavy hittersstreaming

The edge service handles about 3,000 requests per second across roughly 50,000 tenants, peaking near 9,000. Expose the 50 heaviest tenants by request count over the trailing five minutes so limits can be tightened before one tenant's backfill starves the fleet. You may not retain five minutes of raw records. Give the exact solution and its memory, then the bounded-memory approximation with its error stated as a formula, and say which you would ship and at what tenant cardinality that choice changes.

Approach
  1. Do the exact version first, because it is affordable at this cardinality: a ring of 300 one-second counters per tenant, advanced lazily, is 1,200 bytes of counters per tenant and roughly 60 to 90 MB for 50,000 tenants with overhead. Carry a running total and subtract the bucket you overwrite so a window read is O(1) rather than 300 adds.
  2. Extract the top 50 with a size-k min-heap over the tenant sums: O(d log k) for d tenants, against O(d log d) to sort them all. Maintaining the heap continuously instead of on query requires a tenant-to-heap-index map, because incrementing a count already inside the heap means sifting from a known position, and without that map you rebuild the heap on every request.
  3. State the approximation precisely rather than gesturing at sketches. Misra-Gries with m counters retains every item whose true count exceeds N/(m+1), and each retained count underestimates the truth by at most N/(m+1). With m = 1,000 and N = 900,000 requests in the window the error is roughly 900 requests, which is fine for spotting a tenant sending 50,000 and useless for ranking two tenants 200 apart.
  4. Say what breaks when the window slides: Misra-Gries and Space-Saving are insert-only and cannot be decremented as records age out. The workable construction is one summary per sub-window, say ten seconds, with 30 summaries merged at query time, and the merged error is the sum of the per-summary errors, so the bound degrades linearly in the number of sub-windows.
  5. Choose and defend it: at 50,000 tenants the exact rings cost under 100 MB in a process that already holds more, so ship exact. Keep the sketch for the case that actually motivates it, a per-principal or per-IP key where cardinality runs to millions and is not bounded by anything you control.
  6. Raise the fleet problem before it is asked: each of 20 to 40 instances sees only its share, and the top 50 of one shard is not the top 50 of the fleet. Either aggregate counts centrally or accept that a per-instance threshold multiplied by instance count is the limit you are really enforcing.
Worked solution 25 min
  1. Size the exact structure: 300 one-second counters per tenant across 50,000 tenants, plus the running-total trick that makes a window read O(1).
  2. Write the top-k extraction with a size-50 min-heap and compare its complexity against sorting all 50,000 sums.
  3. Substitute N = 900,000 and m = 1,000 into N/(m+1) and state in requests what the sketch can and cannot distinguish.
  4. Write the sub-window merge for the sliding case and state the resulting bound for 30 merged summaries.
EXPECTED RESULTAn exact per-tenant ring of 300 one-second counters at roughly 60 to 90 MB for 50,000 tenants with O(1) window reads, top-50 extraction by a size-k min-heap in O(d log k), a Misra-Gries bound of N/(m+1) with the numbers substituted, the sub-window merge needed to slide it, and a decision to ship exact at this cardinality with the sketch reserved for unbounded keys.
Follow-up
  • The heaviest tenant is heavy because of one export job rather than user traffic. Should the limiter treat those as the same tenant?
  • Two tenants sit tied at the boundary of the top 50. Does your answer flap, and does the flapping matter?
  • You switch to per-principal keys and cardinality goes to 10 million. Walk through what changes.

Four days sample coding, design, fundamentals and the practical rounds at deliberately shallow depth, which is enough to surface the topics you did not know were in scope. That map, rather than a guess made on day one, decides where the last three days go.

Small steps. Visible outcomes.0 / 7 completed
ONE WEEK · YOUR PACE

Prepare, practise & reflect

One practical outcome each day. Spend longer where you need it.

0 / 7 done
01Coding, one pass at shallow depth
  • Solve one problem from each of six families, an array with two pointers, hash counting, binary search, a tree traversal, a graph traversal and one dynamic program, under a hard twenty-minute cap with no extensions, marking each finished, late, or stalled.
  • For every stall, write the exact move you could not make rather than the subject, so the note reads could not turn the recurrence into a loop rather than bad at dynamic programming.
  • Fix nothing today. The value of the pass is the unfixed record.

Deliverable: Six timed attempts marked finished, late or stalled, each stall carrying a named blocking move.

Practice prompt ↗Practice prompt ↗Practice prompt ↗Worked solution ↗
02Design, one pass at shallow depth
  • Spend twenty minutes each on three different shapes, a read-heavy feed, a write-heavy ingest path, and something needing a transaction across two entities, stopping each at requirements, interface and data model.
  • After each, write the first question you could not answer, which is usually a number you could not estimate or a failure mode you had no vocabulary for.
  • Mark which of the three you would be most relieved not to be asked, and treat that as data rather than as a preference.

Deliverable: Three shallow designs, each with the first unanswerable question written at the bottom.

Practice prompt ↗Practice prompt ↗
03Fundamentals and the practical rounds
  • Answer eight short questions in writing at four minutes each, covering the material that fills the gaps between the big rounds: what happens between a URL and a rendered page, what an index costs on write, when a process is preferable to a thread, and what conditions a deadlock requires.
  • Do one thirty-minute practical task of the kind a take-home compresses: read an unfamiliar two-hundred-line file and write what it does, what you would change, and the one thing you remain unsure of.
  • Score every answer fluent, correct but slow, or absent, and keep the absent ones visible.

Deliverable: Eight scored short answers and one written reading of unfamiliar code.

Practice prompt ↗Practice prompt ↗
04The rounds that are about you, and the map
  • Deliver three behavioural answers aloud against a timer, a conflict, a failure you owned, and a decision made without enough information, marking any that ran past three minutes or contained no number.
  • Assemble the map: every marked item from days one to three on a single page, sorted by how likely it is to appear in your loop rather than by how uncomfortable it felt.
  • Choose exactly two areas for the remaining three days and write down what you are deliberately abandoning.

Deliverable: A one-page scored map of the whole surface area with two areas chosen and the rest explicitly abandoned.

Practice prompt ↗Practice prompt ↗Worked solution ↗
05First chosen area, to the depth you skipped
  • Work the higher-ranked area in four focused blocks, choosing items one level above where you stalled rather than repeating what already works.
  • After each block write the rule you extracted in one sentence with its precondition attached, since a rule carrying no precondition is exactly what fails under a variation.
  • Re-attempt the day-one or day-two item that exposed this area and compare against the original timing.

Deliverable: Four worked blocks, a timed re-attempt against the original, and three one-sentence rules with preconditions.

Practice prompt ↗Practice prompt ↗
06Second chosen area, where the gap is coverage rather than speed
  • Treat the second area differently from the first. Day five drilled something you could already half-do; this one is usually a topic you had simply never met, so build one worked reference example end to end and keep it, rather than attempting six problems badly.
  • Write down the vocabulary you were missing on day two or three, five terms at most, each with the one sentence that makes it usable in an answer rather than the textbook definition.
  • Redo the shallow attempt that exposed this area and note whether you now fail later in the problem, because moving the failure point is the realistic gain from a single day and is worth more than a score that did not change.

Deliverable: One worked reference example for the newly covered area, a five-term vocabulary list, and a note on where the failure point moved.

Practice prompt ↗Practice prompt ↗
07Reassemble the loop
  • Sit two rounds back to back with no gap, ordering them so the area you chose second comes last, because the map was built from rested, isolated attempts and the loop will reach your weaker area when you are already spent.
  • Write where the second round suffered from the first, which is normally the point at which structure collapses into narration.
  • Reduce the week to one page holding only the rules you can state without reading them.

Deliverable: Mock notes on cross-round carryover plus a one-page card of rules you can recite from memory.

Practice prompt ↗Practice prompt ↗Worked solution ↗

Expand any day for tasks and deliverables. Your progress is saved on this device.

Bring the two or three numbers the story rests on and know how they were collected. A p99 whose timer starts inside your handler excludes the time a request spent queued, so it can sit flat while users wait longer. Give the window, the percentile and what the measurement left out, or drop the number.

How do you handle boundary conditions and padding when implementing a …

medium
behavioural and collaboration

How do you handle boundary conditions and padding when implementing a custom convolutional operation from scratch?

Approach
  1. Name the disagreement and how you resolved it with evidence.
  2. Give the blast radius: what could have broken, and what you measured.
  3. Pick a story where you made the decision, not one where you watched it.
Follow-up
  • How did you know your change caused the improvement?
  • What would you do differently if you ran that again?

Narrate an outage you owned from page to postmortem

hard
incident responseblast radiuspostmortems

Pick an incident you personally drove, ideally one where writes were affected rather than reads. In six to eight minutes: state the symptom as it first appeared on a dashboard, the blast radius you established before you knew the cause, the mitigation you applied and when, the mechanism you eventually proved, and the follow-up that would prevent a repeat. Bring numbers: error rate, tenants affected, minutes to mitigate, minutes to resolve. If you cannot name what you measured, choose a different incident.

Approach
  1. Open on the signal rather than the cause: which metric at which percentile moved, on which service, at what time, so the listener follows the same evidence you had rather than a conclusion you already reached.
  2. Separate mitigation from diagnosis out loud. State what you did to stop the bleeding (flag off, shed traffic, drain a lease, roll back a deploy) and say plainly that you did it before the mechanism was known, because those are two jobs with different deadlines.
  3. Establish blast radius in countable terms: how many tenants, how many writes, and crucially whether the effect was loss or only delay. An append-only revision table or a pending outbox row means the change survived and the projection was merely behind, which is a repair rather than a data-loss incident.
  4. Prove the mechanism instead of asserting it. Name the trace span that grew, the plan that flipped to a sequential scan, the lease that expired, plus one alternative you ruled out and the signal that stayed flat while you ruled it out.
  5. Close on the durable fix and its cost, distinguishing what landed that week from what needed an expand-and-contract migration across several deploys, and say which of the two you actually finished.
Follow-up
  • What would you do differently in the first five minutes, given the same dashboard and no more information?
  • Which follow-up action did you deliberately not take, and why was dropping it the right call?
  • How did you convince yourself the mitigation was safe to apply while the cause was still unknown?

Turn a code review disagreement into a decision

easy
code reviewoptimistic concurrencycommunication

A colleague's change updates a row with UPDATE resource SET version = version + 1 WHERE resource_id = $1 AND version = $2 and treats an affected-row count of zero as a successful no-op. You read that as a silently lost update; they think returning 200 is friendlier to clients than returning a conflict. Describe how you have handled a review disagreement of this shape: what goes in the comment, when you leave the thread, and who decides. Then write the comment you would leave here, in under 80 words.

Approach
  1. Sort the disagreement before writing anything. A silently discarded write is a correctness claim about data; the choice between 409 and 412 is taste. Only the first justifies blocking a merge, and saying which one you are doing is most of the value of the comment.
  2. Make the claim reproducible in the comment itself with an interleaving rather than a principle: A reads version 7, B reads version 7, B commits version 8, A's predicate matches zero rows, A is told it succeeded and A's edit is gone.
  3. Offer the alternative with its cost attached: return 409 carrying the current version and the revision that won, so the client can re-read and re-apply. Note that automatic retry is not the fix, because a retry re-reads the winner's state and reapplies an intent formed against data that no longer exists.
  4. Apply an escalation rule you can state: two round trips on the thread, then a call, and the service's owner decides rather than the reviewer. A reviewer who cannot be overruled is a bottleneck with extra steps.
  5. Close in writing wherever the decision lands, so the next reader finds the reasoning in the code or the ticket instead of in a collapsed review thread.
Follow-up
  • Where would you put the test that fails if someone reintroduces the swallowed zero rowcount?
  • The author says clients cannot handle a 409. How do you check whether that is true?
  • How do you handle the same review comment when the author is more senior than you and in a hurry?
  • 01

    How do you handle boundary conditions and padding when implementing a custom convolutional operation from scratch?

  • 02

    Pick an incident you personally drove, ideally one where writes were affected rather than reads. In six to eight minutes: state the symptom as it first appeared on a dashboard, the blast radius you established before you knew the cause, the mitigation you applied and when, the mechanism you eventually proved, and the follow-up that would prevent a repeat. Bring numbers: error rate, tenants affected, minutes to mitigate, minutes to resolve. If you cannot name what you measured, choose a different incident.

  • 03

    A colleague's change updates a row with UPDATE resource SET version = version + 1 WHERE resource_id = $1 AND version = $2 and treats an affected-row count of zero as a successful no-op. You read that as a silently lost update; they think returning 200 is friendlier to clients than returning a conflict. Describe how you have handled a review disagreement of this shape: what goes in the comment, when you leave the thread, and who decides. Then write the comment you would leave here, in under 80 words.

PracHub interview preparation framework ↗
Is this an official Imagry interview guide?

No. It is PracHub's own research and practice material for the Machine Learning Engineer role at Imagry. Rounds and questions reflect what candidates have reported, not a process Imagry has published, and they change over time. Confirm the current format and scope with your recruiter.

PracHub interview research ↗
How much C++ knowledge is required compared to Python?

Both are highly critical. While Python is primarily used for rapid prototyping, research, and model training, C++ is the primary language used for production deployment at Imagry. You must be comfortable writing, debugging, and optimizing production-grade C++ code.

PracHub interview research ↗
What is the typical difficulty level of the interview process?

The process is generally rated as difficult due to its emphasis on low-level implementation and fundamental mathematical concepts. Candidates who rely solely on high-level APIs without understanding the underlying mechanics often find the technical rounds challenging.

PracHub interview research ↗
How can I best prepare for the practical task in the interview?

Practice implementing basic neural network operations (such as convolutions, pooling, and matrix multiplication) from scratch in C++. Focus on writing clean, modular code and pay close attention to boundary conditions, memory allocation, and execution efficiency.

PracHub interview research ↗
What is the working culture like for engineers at Imagry?

The engineering culture is highly collaborative, fast-paced, and driven by a shared passion for solving complex physical-world problems. Engineers enjoy a high degree of ownership over their projects and work in a flat organizational structure where technical excellence is highly valued.

PracHub interview research ↗
Sources & methodology 3 sources ↗

No official company page is cited. Rounds and questions come from candidate reports and PracHub editorial material; each source shows the date it was read.