Discovery feed ranking
Design the ML-ranked feed for a short-video app with 200M DAU where the feed is pure discovery (not follow-based) — every scroll picks the next best video from a 1B-video corpus. Optimize for watch-time and meaningful engagement, serve the next video in under 100ms, and incorporate integrity (don't over-amplify borderline/harmful content).
What a strong answer looks like
Clarify scale and constraints first. Propose a clean component breakdown, then go deep on the hard parts (data model, bottlenecks, consistency, failure modes) and name the trade-offs you are making.
Clarify6:00 left
Estimate6:00 planned
Design18:30 planned
Deep dive14:30 planned
Failure10:00 planned
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.