Content moderation at scale
Design a content-moderation pipeline for a social platform that ingests ~5,000 user posts/sec, each potentially containing text, images, and short video. The system must block clearly-violating content (e.g. CSAM, graphic violence) before it goes live with high recall, route borderline cases to human reviewers, and keep median time-to-decision low so legitimate posts aren't delayed. Policies change frequently, different regions have different rules, and you must keep an auditable record of every automated and human decision for appeals and regulators.
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.