← Google Interview Insights

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

SeniorPrefer not to say
May 2026

Summary

Google system design round, one big question about predicting Netflix watch times. Not a lot of context given upfront and I probably spent too long on the ML side when they clearly wanted to talk infrastructure.

Questions Asked (1)

Q1

Design a system to predict Netflix watch times.

System DesignTechnical Trade-offsData Modeling
Author's notes

I started with data collection and feature engineering, which felt natural, but about 15 minutes in I realized I hadn't touched on serving latency or how predictions would actually get surfaced to users in real time.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the business objective and success metrics, then outline the end-to-end ML pipeline from data collection to deployment. Focus on feature engineering, model choices, and evaluation specific to watch time prediction, while discussing trade-offs and scalability.

Pro tip: Emphasize that watch time is a proxy for engagement and that you would design the system to optimize long-term user satisfaction, not just immediate clicks. Mention the importance of handling implicit feedback and potential biases in the data.

1. Clarify Requirements and Metrics

Define what 'watch time' means (e.g., total minutes watched per session, per user, per title) and the prediction granularity. Identify business goals and success metrics like RMSE, MAE, or ranking metrics if used for recommendations.

2. Data Collection and Feature Engineering

Identify data sources: user interactions (views, pauses, skips), content metadata, user demographics, and contextual data. Engineer features such as historical watch time, user activity patterns, content popularity, and temporal features.

3. Model Selection and Training

Choose appropriate models: start with baselines (e.g., global average, matrix factorization), then consider advanced models like gradient boosted trees, deep neural networks, or sequence models (RNNs, Transformers) for temporal patterns. Address cold-start and scalability.

4. Evaluation and Validation

Use offline evaluation with time-based splits to mimic production. Consider online A/B testing to measure impact on user engagement. Monitor for bias and ensure model robustness.

5. Deployment and Monitoring

Design a serving architecture for low-latency predictions, possibly with batch pre-computation. Set up monitoring for data drift, model performance, and business metrics, with retraining pipelines.

Key Points to Mention

  • Handling implicit feedback and defining negative samples
  • Feature engineering: session-based features, time decay, content embeddings
  • Model choices: collaborative filtering, deep learning for sequences, and hybrid approaches
  • Evaluation metrics: RMSE, MAE, and business metrics like user retention
  • Scalability: distributed training, online serving, and caching
  • Ethical considerations: avoiding feedback loops and ensuring diversity in recommendations

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