Content artwork optimization and convergence
Design the system that decides which thumbnail/title artwork to show for each piece of content on a streaming homepage. New titles arrive constantly with no engagement data, you have dozens of artwork variants per title, and you want to converge fast on the best variant per title while not wasting too many impressions on bad variants — and you must avoid permanently locking in a variant that only looked good early by chance. Design the online optimization system and contrast it with running a fixed A/B test per title.
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.
Clarify5:00 left
Estimate5:00 planned
Design15:00 planned
Deep dive12:00 planned
Failure8:00 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.