End-to-End Design
Design search over a social product's posts: a user types a multi-word query and gets back the most relevant posts, ranked, out of a corpus of billions that grows every second.
In scope: indexing new posts so they become searchable, answering a full-text keyword query with ranked results, and keeping the index current as posts keep arriving. Out of scope: deep personalization, image or video search, spell-correction and query understanding, and the internals of the learned ranking model.
What a strong answer sounds like
State the decision, connect it to a requirement, and name the tradeoff. Keep the design focused on the workload in the prompt.
The AI interviewer asks about this part of Design Post Search (Full-Text Search). The interviewer guides you through topics one by one.