Design the request router and scheduler for a multi-replica LLM serving cluster.
Round-robin routing throws away a feature that doubles throughput: cache locality. Designing the router means picking a replica by KV state, not just least-loaded. Here is the two-layer design.
Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.
Round-robin routing throws away a feature that doubles throughput: cache locality. Designing the router means picking a replica by KV state, not just least-loaded. Here is the two-layer design.
Lead with where the obvious approach breaks, because that is the judgment they are screening for — most candidates jump straight to the happy path and lose the room.
Then walk the failure back through the pipeline in order, naming the one metric the customer's exec sponsor actually cares about before you propose the fix.
