PracHub
QuestionsPremiumLearningGuidesCheatsheetNEWCoaches
|Home/ML System Design/Snapchat

Design an ads ranking ML system

Last updated: Mar 29, 2026

Quick Overview

This question evaluates a candidate's ability to design a low-latency ads ranking machine learning system, including feature engineering and freshness, training-data construction under position and selection bias, multi-objective modeling and multi-task architectures, and production issues like cold start, delayed conversions, distribution shift, and feature leakage. It is commonly asked in ML System Design interviews for Machine Learning Engineer roles to assess trade-offs between long-term business metrics and user experience, evaluation and guardrails for offline and online experiments, and both conceptual understanding and practical application in engineering and modeling decisions.

  • medium
  • Snapchat
  • ML System Design
  • Machine Learning Engineer

Design an ads ranking ML system

Company: Snapchat

Role: Machine Learning Engineer

Category: ML System Design

Difficulty: medium

Interview Round: Onsite

## Prompt You are designing an **ads ranking** system for a large consumer app (feed/search entry point). For each request, the system receives a user context and a set of eligible ads/candidates and must return a ranked list of ads. ### Requirements - Primary business goal: maximize long-term value (e.g., revenue) while maintaining good user experience. - Must handle multiple optimization targets such as **CTR**, **CVR**, and **expected revenue**. - Latency budget: tens of milliseconds for the ranking stage (assume candidate generation is separate). - Strong emphasis on ML aspects: **feature design**, **training data**, **modeling choices**, and **multi-task learning**. ### Questions to answer 1. What features would you build (user/ad/context/cross features) and how would you generate and keep them fresh? 2. How would you define labels and build training data given bias from the existing ranker (position bias / selection bias)? 3. Propose a ranking model and explain how you’d combine multiple objectives (e.g., CTR + CVR + value). If using **multi-task learning**, describe the architecture and loss. 4. How would you evaluate the model offline and online? What key metrics and guardrails would you use? 5. How would you handle practical issues: cold start, delayed conversions, distribution shift, and feature leakage?

Quick Answer: This question evaluates a candidate's ability to design a low-latency ads ranking machine learning system, including feature engineering and freshness, training-data construction under position and selection bias, multi-objective modeling and multi-task architectures, and production issues like cold start, delayed conversions, distribution shift, and feature leakage. It is commonly asked in ML System Design interviews for Machine Learning Engineer roles to assess trade-offs between long-term business metrics and user experience, evaluation and guardrails for offline and online experiments, and both conceptual understanding and practical application in engineering and modeling decisions.

Related Interview Questions

  • Design User Embedding Semantic Search - Snapchat (medium)
  • Design a Family-Friendly Listing Classifier - Snapchat (medium)
  • Design a video recommendation system - Snapchat (medium)
  • Design short-video retrieval with sparse text - Snapchat (medium)
  • Design a Product Tagging Pipeline - Snapchat (medium)
Snapchat logo
Snapchat
Feb 11, 2026, 12:00 AM
Machine Learning Engineer
Onsite
ML System Design
6
0
Loading...

Prompt

You are designing an ads ranking system for a large consumer app (feed/search entry point). For each request, the system receives a user context and a set of eligible ads/candidates and must return a ranked list of ads.

Requirements

  • Primary business goal: maximize long-term value (e.g., revenue) while maintaining good user experience.
  • Must handle multiple optimization targets such as CTR , CVR , and expected revenue .
  • Latency budget: tens of milliseconds for the ranking stage (assume candidate generation is separate).
  • Strong emphasis on ML aspects: feature design , training data , modeling choices , and multi-task learning .

Questions to answer

  1. What features would you build (user/ad/context/cross features) and how would you generate and keep them fresh?
  2. How would you define labels and build training data given bias from the existing ranker (position bias / selection bias)?
  3. Propose a ranking model and explain how you’d combine multiple objectives (e.g., CTR + CVR + value). If using multi-task learning , describe the architecture and loss.
  4. How would you evaluate the model offline and online? What key metrics and guardrails would you use?
  5. How would you handle practical issues: cold start, delayed conversions, distribution shift, and feature leakage?

Solution

Show

Comments (0)

Sign in to leave a comment

Loading comments...

Browse More Questions

More ML System Design•More Snapchat•More Machine Learning Engineer•Snapchat Machine Learning Engineer•Snapchat ML System Design•Machine Learning Engineer ML System Design
PracHub

Master your tech interviews with 7,500+ real questions from top companies.

Product

  • Questions
  • Learning Tracks
  • Interview Guides
  • Resources
  • Premium
  • For Universities
  • Student Access

Browse

  • By Company
  • By Role
  • By Category
  • Topic Hubs
  • SQL Questions
  • Compare Platforms
  • Discord Community

Support

  • support@prachub.com
  • (916) 541-4762

Legal

  • Privacy Policy
  • Terms of Service
  • About Us

© 2026 PracHub. All rights reserved.