← Airbnb Interview Insights

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

SeniorPrefer not to say
Jun 2026

Summary

Round 3 of the Airbnb ML Engineer loop was a deep system design session focused on retrieval and ranking, and it ran long. They clearly care a lot about marketplace ranking experience, so if that's not your background, you'll feel it.

Questions Asked (2)

Q1

Design a user embedding and two-stage semantic retrieval and ranking system to surface listings a user is most likely to book, with the goal of maximizing booking conversion.

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

This was the whole round basically.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the business goal and constraints, then outline a two-stage architecture: a fast candidate generation stage using user and listing embeddings, followed by a more complex ranking model. Emphasize how each stage optimizes for booking conversion, and discuss trade-offs between latency, accuracy, and scalability.

Pro tip: Highlight the importance of negative sampling and how you would handle position bias in ranking, as these are common pitfalls in real-world retrieval systems. Also, mention how you would incorporate real-time user behavior signals to adapt embeddings dynamically.

1. Clarify Requirements and Metrics

Ask about scale (users, listings), latency requirements, and definition of booking conversion. Identify key metrics like recall@k for retrieval and NDCG for ranking.

2. Design Embedding Models

Propose learning user and listing embeddings using collaborative filtering or two-tower neural networks. Discuss features (user history, listing attributes) and training objectives (e.g., binary cross-entropy on bookings).

3. Two-Stage Retrieval and Ranking

Describe candidate generation via approximate nearest neighbor search on embeddings, then a ranking model (e.g., GBDT or deep neural network) that uses richer features to predict booking probability.

4. Address Trade-offs and Challenges

Discuss trade-offs: embedding dimensionality vs. latency, model complexity vs. interpretability, and cold-start handling. Mention techniques like negative sampling, position bias correction, and online learning.

5. Evaluate and Iterate

Outline offline evaluation (A/B tests, counterfactual logging) and online metrics (CTR, booking rate). Suggest monitoring and retraining cadence to adapt to changing user preferences.

Key Points to Mention

  • Two-tower architecture for user and listing embeddings
  • Approximate nearest neighbor (ANN) for efficient retrieval
  • Negative sampling strategies for training embeddings
  • Ranking model features: user-listing interactions, context, and real-time signals
  • Handling position bias and feedback loops in ranking
  • Latency and scalability considerations in production

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

Q2

How do you handle position bias in a click-based training signal for a ranking model?

A/B Testing & ExperimentationTechnical Trade-offsSystem Design
Author's notes

This is where the interviewer really pushed.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by defining position bias and its impact on click data, then outline a multi-faceted approach combining modeling and experimentation. Emphasize practical techniques like position-based features, counterfactual methods, and validation through A/B tests, tailored to Airbnb's ranking context.

Pro tip: Highlight the importance of logging randomization data (e.g., from exploration) to enable unbiased evaluation, and mention that position bias mitigation should be validated with online metrics like booking rate, not just click metrics.

1. Define and Diagnose Position Bias

Explain what position bias is in click data and how it manifests in ranking models. Discuss methods to detect it, such as examining click-through rates by position or using randomization data.

2. Modeling Approaches to Mitigate Bias

Describe techniques like adding position as a feature during training but removing it at inference, or using counterfactual methods (e.g., inverse propensity scoring) to reweight clicks.

3. Leverage Experimental Data

Utilize data from A/B tests or exploration traffic where positions are randomized to train unbiased models or evaluate debiasing techniques.

4. Validate and Iterate

Evaluate the debiased model offline using unbiased metrics and online through A/B tests, monitoring business metrics like bookings. Iterate based on results.

Key Points to Mention

  • Position bias definition: users click higher-ranked items more often regardless of relevance.
  • Inverse Propensity Scoring (IPS) and its variants for debiasing click data.
  • Using position as a feature during training but not at inference (position-aware training).
  • Randomization or exploration data to obtain unbiased click signals.
  • Offline evaluation with unbiased metrics (e.g., from randomized data) and online A/B testing.
  • Trade-offs: complexity, potential for overcorrection, and impact on business metrics.

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