← Meta Interview Insights

Meta·Machine Learning Engineer·Technical Phone Screen·Senior

Senior
May 2026

Summary

Interviewed for an ML engineer role at Meta and got asked about production model testing. Pretty focused session, just the one technical area but they went deep on it.

Questions Asked (1)

Q1

How do you test your machine learning models before deploying them to production?

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

This is broader than it sounds.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Structure your answer around a layered testing strategy that progresses from offline evaluation to online experimentation, emphasizing how each layer mitigates different risks. Highlight the importance of aligning offline metrics with online business metrics and the role of continuous monitoring post-deployment.

Pro tip: At Meta, scale and low latency are critical, so mention how you test for performance and fairness at scale, and how you use counterfactual logging and interleaving to speed up experimentation.

1. Offline Evaluation

Start with offline testing using a held-out test set and cross-validation to assess model performance on metrics like accuracy, precision, recall, and AUC. Ensure data splits are representative and consider temporal splits for time-series data.

2. Robustness and Fairness Checks

Evaluate model robustness to distribution shifts, adversarial examples, and edge cases. Also, assess fairness across different user segments to avoid bias and ensure compliance with ethical guidelines.

3. Online A/B Testing

Deploy the model to a small percentage of traffic in a controlled A/B test, comparing it against the current production model. Define primary and guardrail metrics, and ensure sufficient statistical power to detect meaningful differences.

4. Scalability and Latency Testing

Test the model's inference latency and throughput under production-like load to ensure it meets performance requirements. Use load testing and profiling to identify bottlenecks.

5. Monitoring and Iteration

After full deployment, continuously monitor model performance, data drift, and business metrics. Set up alerts for anomalies and establish a feedback loop for retraining and improvement.

Key Points to Mention

  • Offline metrics (e.g., AUC, F1) and their limitations
  • Online metrics (e.g., CTR, conversion rate) and business impact
  • A/B testing methodology, including sample size and duration
  • Guardrail metrics to detect negative impacts
  • Model interpretability and fairness assessments
  • Monitoring for data drift and model degradation

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