How do you autoscale LLM inference, and why is it different from scaling a normal web service?
CPU-based autoscaling that suits a web tier quietly breaks on GPU inference: the signal is wrong, and replicas need minutes to warm. The interviewer wants the signals you genuinely scale on and how you mask the cold start.
Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.
CPU-based autoscaling that suits a web tier quietly breaks on GPU inference: the signal is wrong, and replicas need minutes to warm. The interviewer wants the signals you genuinely scale on and how you mask the cold start.
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.
