← Meta Interview Insights

Meta·Machine Learning Engineer·Onsite - System Design / Architecture·Senior

SeniorPrefer not to say
May 2026

Summary

ML system design round at Meta, two big topics back to back: recommendation systems and notification ranking. Discussion-style, so less 'here's my answer' and more going back and forth with the interviewer. Felt like the kind of session where knowing the vocabulary matters as much as knowing the concepts.

Questions Asked (3)

Q1

Design a short-video recommendation system (think TikTok or Instagram Reels style). Walk through your architecture end to end.

System DesignTechnical Trade-offsProduct Analytics & Metrics
Author's notes

This is the bread and butter of ML design rounds at big social platforms, so I wasn't surprised.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying requirements and scale, then walk through the end-to-end ML pipeline from candidate generation to ranking and serving, emphasizing trade-offs at each stage. Highlight how you would measure success and iterate using online metrics and A/B testing.

Pro tip: Anchor your design around the user's short-term and long-term satisfaction, not just click-through rate, and mention how you'd balance exploration and exploitation to avoid feedback loops.

1. Clarify Requirements and Scale

Ask about scale (DAU, videos), latency constraints, and business goals (engagement, retention). Define success metrics like watch time, completion rate, and user satisfaction.

2. High-Level Architecture

Outline the main components: candidate generation (retrieval), ranking, re-ranking, and serving. Mention data pipelines for training and feature engineering.

3. Candidate Generation

Describe multiple retrieval sources (e.g., collaborative filtering, content-based, trending, social graph) and how to combine them efficiently using ANN or inverted indices.

4. Ranking and Re-ranking

Explain the ranking model (e.g., deep neural network with multi-task learning) and re-ranking for diversity, freshness, and business rules. Discuss feature engineering and model training.

5. Serving, Evaluation, and Iteration

Cover low-latency serving, online A/B testing, and offline evaluation. Discuss how to monitor and mitigate feedback loops and biases.

Key Points to Mention

  • Two-stage or multi-stage architecture: retrieval then ranking
  • Use of embeddings and approximate nearest neighbor search for candidate generation
  • Multi-task learning to optimize for multiple objectives (e.g., likes, shares, watch time)
  • Exploration vs exploitation to handle cold start and feedback loops
  • Online metrics (e.g., watch time, retention) and A/B testing framework
  • Scalability and latency considerations (e.g., caching, model serving optimizations)

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q2

How would you design a nearby-place recommendation feature? What changes compared to a standard content recommendation system?

System DesignTechnical Trade-offs
Author's notes

Shorter discussion than the video one.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by outlining the core components of a nearby-place recommendation system: data sources (user location, place attributes, user preferences), candidate generation (spatial indexing), ranking (personalization and context), and evaluation. Then contrast it with standard content recommendation, emphasizing the unique challenges of geospatial data, real-time constraints, and the importance of distance and freshness.

Pro tip: Highlight the trade-off between exploration and exploitation in a spatial context: users may be willing to travel farther for highly relevant places, but distance decay must be modeled. Also, mention the cold-start problem for new places and how to leverage geographic features.

1. Clarify Requirements and Scope

Ask clarifying questions about scale (number of users, places), latency requirements, data availability (user history, place metadata), and business goals (e.g., increase engagement, drive foot traffic).

2. Data and Feature Engineering

Identify key data: user location (GPS, check-ins), place attributes (category, ratings, popularity), user preferences (historical interactions), and contextual signals (time of day, weather). Discuss geospatial feature engineering like distance, density, and neighborhood embeddings.

3. System Architecture

Outline a two-stage architecture: candidate generation using spatial indexing (e.g., geohash, Quadtree) to retrieve nearby places, followed by ranking with a machine learning model that incorporates distance, personalization, and context.

4. Modeling and Ranking

Explain how to model distance decay (e.g., exponential decay), incorporate user-item interactions, and handle cold-start for new places. Discuss model choices (e.g., GBDT, neural networks) and how to combine features.

5. Evaluation and Iteration

Define offline metrics (e.g., recall@k, NDCG) and online metrics (CTR, conversion, user engagement). Discuss A/B testing, handling position bias, and continuous improvement.

Key Points to Mention

  • Geospatial indexing techniques (geohash, Quadtree, R-tree) for efficient candidate retrieval.
  • Distance decay modeling: how proximity affects user choice, and the need to balance relevance and distance.
  • Real-time constraints: low-latency serving, handling dynamic user locations, and streaming updates.
  • Cold-start problem for new places: leveraging content-based features and geographic context.
  • Evaluation challenges: location-based biases, sparsity of interactions, and the need for online metrics.
  • Differences from standard recommendation: spatial context, distance as a primary factor, and the importance of freshness and local trends.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q3

Given a mix of notification types (likes, comments, friend activity, ads, system messages), how would you rank and decide which notifications to send to a user and when?

System DesignTechnical Trade-offsProduct Analytics & Metrics
Author's notes

Harder than it sounds because it's not just ranking, it's also a multi-objective problem with fatigue and unsubscription risk baked in.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by framing the problem as a ranking and optimization challenge with multiple objectives: user engagement, satisfaction, and business value. Propose a machine learning system that scores each notification based on predicted user interaction and utility, then applies constraints like frequency capping and timing optimization. Emphasize the need for a multi-objective approach that balances short-term metrics with long-term user retention.

Pro tip: Highlight the importance of negative feedback signals (e.g., dismissals, opt-outs) and long-term user satisfaction metrics, not just click-through rates, to avoid optimizing for short-term engagement at the expense of user trust.

1. Define Objectives and Metrics

Clarify the goals: maximize user engagement (e.g., clicks, comments), user satisfaction (e.g., reduced notification fatigue), and business value (e.g., ad revenue). Define metrics like CTR, conversion rate, dismissal rate, and long-term retention.

2. Feature Engineering and Scoring

For each notification, compute features: user-notification affinity (historical interactions), content type, recency, urgency, and contextual factors (time of day, device). Train a model to predict the probability of positive user action (e.g., click) and negative action (e.g., dismiss).

3. Ranking and Selection

Combine scores into a utility function that balances predicted engagement and user value. Rank notifications by utility, then select top ones subject to constraints like frequency caps, diversity, and timing rules.

4. Timing Optimization

Determine the optimal time to send each notification using models that predict user responsiveness by time of day, day of week, and user activity patterns. Consider batching to avoid overwhelming the user.

5. Evaluation and Iteration

Evaluate the system via online A/B tests measuring both short-term engagement and long-term user satisfaction (e.g., retention, notification opt-out rates). Continuously refine models with feedback loops.

Key Points to Mention

  • Multi-objective optimization: balancing engagement, user satisfaction, and business goals.
  • Use of machine learning models for predicting click-through rate (CTR) and negative feedback (e.g., dismissals).
  • Importance of frequency capping and timing to prevent notification fatigue.
  • Leveraging contextual features: user activity, time of day, device type.
  • Online evaluation with A/B testing and guardrail metrics to monitor long-term impact.
  • Handling different notification types: likes, comments, ads, etc., with type-specific models or features.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.