Preview build — question counts, lessons, and company notes on this site are placeholder data, not verified interview content.
Indwar

Cut p99 serving latency in half

ML designHardCorroborated · 4 reportsLast seen Aug 27, 2026

The question

An inference service meets its p50 target but misses p99 by 3x. Walk through how you would diagnose it, then which of batching, caching, quantisation, or admission control you would reach for and why.

No write-up yet

We have the question but not yet a full breakdown. If you were asked this, the fastest way to improve the page is to say what the interviewer pushed on.

Add what you remember →

4 people reported this question.

I was asked this too

Also reported at Anthropic, Netflix, Perplexity, xAI.

Study the fundamentals: ML systems