Your question is Real-Time Recommendation at Scale. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
How would you build a real-time recommendation system that scales to handle millions of active users with low latency?
Explain the end-to-end architecture, including candidate retrieval, ranking, re-ranking, feature management, and model serving. Discuss offline training, online inference, evaluation, monitoring, and failure handling. State the assumptions you would clarify before selecting capacity, latency targets, and model complexity.