Software Engineer Machine Learning Interview Questions
Practice the exact questions companies are asking right now.
"10 years of experience but never worked at a top company. PracHub's senior-level questions helped me break into FAANG at 35. Age is just a number."
"I was skeptical about the 'real questions' claim, so I put it to the test. I searched for the exact question I got grilled on at my last Meta onsite... and it was right there. Word for word."
"Got a Google recruiter call on Monday, interview on Friday. Crammed PracHub for 4 days. Passed every round. This platform is a miracle worker."
"I've used LC, Glassdoor, and random Discords. Nothing comes close to the accuracy here. The questions are actually current — that's what got me. Felt like I had a cheat sheet during the interview."
"The solution quality is insane. It covers approach, edge cases, time complexity, follow-ups. Nothing else comes close."
"Legit the only resource you need. TC went from 180k -> 350k. Just memorize the top 50 for your target company and you're golden."
"PracHub Premium for one month cost me the price of two coffees a week. It landed me a $280K+ starting offer."
"Literally just signed a $600k offer. I only had 2 weeks to prep, so I focused entirely on the company-tagged lists here. If you're targeting L5+, don't overthink it."
"Coaches and bootcamp prep courses cost around $200-300 but PracHub Premium is actually less than a Netflix subscription. And it landed me a $178K offer."
"I honestly don't know how you guys gather so many real interview questions. It's almost scary. I walked into my Amazon loop and recognized 3 out of 4 problems from your database."
"Discovered PracHub 10 days before my interview. By day 5, I stopped being nervous. By interview day, I was actually excited to show what I knew."
"I recently cleared Uber interviews (strong hire in the design round) and all the questions were present in prachub."
"The search is what sold me. I typed in a really niche DP problem I got asked last year and it actually came up, full breakdown and everything. These guys are clearly updating it constantly."
Implement and Debug Backprop in NumPy
Two-Layer Neural Network: Backpropagation and Gradient Check (NumPy) Context You are implementing a fully connected two-layer neural network for multi...
Debug a GRPO training loop and explain ratios
You are given a simplified implementation of a GRPO (Group Relative Policy Optimization) training step for an RLHF-style policy model. The training is...
Build a Heart Disease Baseline
You are given a tabular dataset for predicting whether a patient has heart disease. The dataset contains a binary target column such as has_heart_dise...
Debug a Machine Learning Pipeline
Debugging a Sudden Accuracy Drop in a Deployed ML Pipeline Context You are on-call for a production machine learning service. Monitoring alerts show t...
Implement and derive backprop from scratch
Tiny Neural Network (From First Principles): Binary Classification Context You will implement and analyze a minimal neural network for binary classifi...
Explain overfitting, regularization, and LLM techniques
You’re in an ML interview. Answer the following conceptual questions clearly and concisely, using examples where helpful: 1) Model fit - What is overf...
Explain normalization, regularization, CTR, imbalance handling
You are interviewing for an applied ML role. Answer the following fundamentals clearly and concretely (you may use equations and practical examples): ...
Debug a failing ML classifier
Debugging a Churn Prediction Pipeline With Poor Generalization Context You are evaluating a binary churn prediction system with: - Training ROC AUC: 0...
Explain LLM fine-tuning and generative models
Machine Learning fundamentals (LLM / Generative AI track) You are interviewed for an ML role focused on LLMs and generative AI. Part A — LLM fine-tuni...
Implement and analyze custom attention
Implement Scaled Dot-Product Attention in PyTorch (from scratch) Context You will implement a numerically stable, vectorized scaled dot-product attent...
Design sequence decoding with greedy and beam search
Next-Token Decoding: Greedy and Beam Search Context You are given a probabilistic next-token dictionary D that maps each token t to a dictionary of ca...
How would you model stock price prediction?
Scenario You are asked to use machine learning to predict stock prices (or more realistically, predict future returns / price direction) for a trading...
Derive MLP shapes and explain PyTorch broadcasting
You are given a standard MLP layer (fully connected layer) used in deep learning. 1. Write the forward computation for a linear layer with bias. 2. Gi...
Find minimum of unknown convex function
You are given access to an unknown univariate convex function \(f(x)\) defined on a closed interval \([L, R]\) on the real line. - You cannot see the ...
Implement multi-head self-attention correctly
Implement Multi-Head Self-Attention (from scratch) Context You are given an input tensor X with shape (batch_size, seq_len, d_model). Implement a mult...
Explain learning paradigms, loss, and embeddings
ML fundamentals (oral) Answer the following conceptual questions clearly and with examples: 1. What is supervised learning? What are typical inputs/la...
Implement AUC-ROC, softmax, and logistic regression
You are asked to implement a few core ML building blocks from scratch (no ML libraries such as scikit-learn). You may use basic numeric operations and...
Build a bigram next-word predictor with weighted sampling
You are given a training set of token sequences (sentences), for example: ` [["a","b","c"], ["a","s","d"]] ` 1) Train a simple next-word prediction m...
Explain Transformers and QKV matrices
Transformer Self-Attention: Q, K, V, Multi-Head, and Positional Encoding Context: You are given a sequence of token embeddings X (length n, model dime...
How would you evaluate an AI feature?
You’re building an AI-powered feature (e.g., an AI assistant or AI-enhanced search). Interviewers ask: “How do you measure results and compare metrics...