Your question is System Design Round. 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).
Explain how you would design an end-to-end machine learning system. Clarify requirements before proposing an architecture, and cover data collection, training, model selection, serving, evaluation, monitoring, and failure handling. Discuss online versus batch components, retrieval and ranking stages where appropriate, feature freshness, training-serving skew, and operational tradeoffs. State assumptions explicitly when requirements such as traffic, latency, catalog size, or availability are unspecified.