← Amazon Interview Insights

Amazon·Software Engineer·Technical Phone Screen·Senior

Senior
Jun 2026

Summary

Applied Scientist loop at Amazon, science breadth round covering ML system design with a focus on search and ranking, plus some experimentation case work and behavioral questions. Pretty sparse on details but enough to get a sense of the shape of it.

Questions Asked (2)

Q1

Design an ML system for a search or ranking use case.

System DesignTechnical Trade-offs
Author's notes

This is the core of the round apparently.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the search/ranking use case, scale, and business objectives (e.g., product search on Amazon). Then outline a two-stage architecture: candidate generation (retrieval) and ranking (scoring), and discuss trade-offs in model choice, features, and evaluation. Emphasize how you would iterate and measure success with offline and online metrics.

Pro tip: Anchor your design in Amazon's leadership principles: customer obsession (relevance), ownership (end-to-end metrics), and bias for action (start simple, iterate). Mention how you'd handle cold start and feedback loops to show depth.

1. Clarify Requirements and Scope

Ask questions to understand the use case: what is being searched/ranked (e.g., products, documents), scale (QPS, catalog size), latency constraints, and business metrics (CTR, conversion). Define success criteria and constraints.

2. High-Level Architecture

Propose a two-stage system: candidate generation (retrieval) to narrow millions of items to hundreds, then ranking to order them. Mention components like query understanding, feature store, and serving infrastructure.

3. Candidate Generation (Retrieval)

Describe methods: inverted index (BM25) for lexical, embeddings (two-tower) for semantic, and hybrid. Discuss trade-offs: recall vs. latency, and how to handle cold start.

4. Ranking Model

Explain the ranking model: e.g., gradient boosted trees or deep neural networks (DNN) with features like query-item relevance, user history, item popularity. Discuss multi-objective optimization (relevance, revenue) and business rules.

5. Evaluation and Iteration

Cover offline metrics (NDCG, MRR) and online A/B testing (CTR, conversion). Discuss feedback loops, position bias, and how to monitor and retrain models.

Key Points to Mention

  • Two-stage architecture: retrieval then ranking
  • Feature engineering: query features, item features, user features, cross features
  • Model choices: BM25, two-tower embeddings, GBDT, DNN, learning to rank
  • Evaluation metrics: offline (NDCG, recall@k) and online (CTR, conversion, revenue)
  • Scalability and latency: sharding, caching, approximate nearest neighbors (ANN)
  • Cold start and feedback loops: handling new items/users, position bias correction

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

Q2

Walk through how you would design or evaluate an experiment for a ranking or search system.

A/B Testing & ExperimentationSystem Design
Author's notes

Experimentation in ranking is genuinely tricky because standard A/B tests can have interference effects and position bias makes metrics noisy.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the goal and metrics, then outline a structured experiment design covering hypothesis, randomization, and statistical analysis. Emphasize online A/B testing with guardrail metrics and discuss how to evaluate results for ranking/search systems.

Pro tip: Highlight the importance of defining a clear, single primary metric and pre-registering the experiment to avoid p-hacking. Also, mention that you would run a power analysis to determine sample size and duration.

1. Define Objective and Hypothesis

Clarify the business goal and formulate a testable hypothesis. Identify the primary metric (e.g., CTR, conversion) and guardrail metrics (e.g., latency, revenue).

2. Design Experiment

Choose the experiment type (e.g., A/B test), define control and treatment groups, and determine randomization unit (e.g., user, session). Ensure proper sampling and avoid biases.

3. Determine Sample Size and Duration

Perform power analysis to calculate required sample size and experiment duration. Consider traffic, effect size, and significance level to ensure valid results.

4. Execute and Monitor

Launch the experiment, monitor for technical issues, and track guardrail metrics. Ensure data quality and check for sample ratio mismatch (SRM).

5. Analyze and Decide

Analyze results using statistical tests (e.g., t-test), check for significance and practical impact. Consider segment analysis and decide whether to launch, iterate, or abandon.

Key Points to Mention

  • A/B testing methodology and randomization
  • Primary and guardrail metrics (e.g., CTR, latency, revenue)
  • Statistical significance, power analysis, and p-values
  • Sample ratio mismatch (SRM) and data quality checks
  • Segment analysis and heterogeneous treatment effects
  • Ethical considerations and long-term impact

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