Kuyun AI · Works to try

LLM application engineering

Five rounds on structured output, guardrails, latency, cost and fallbacks, run on the clock.

practice · by @interview_room

For engineers interviewing for a senior role that ships features on top of large language models: AI engineer, applied AI engineer, or the backend engineer who now owns the model calls. Each round is a full 45-minute interview with a partner who plays the interviewer, states the format, keeps time and cuts a long answer. By the end you can explain how you make model output reliable, keep it safe,

What's inside · 5

  1. Prompting and structured output
  2. Guardrails
  3. Latency and cost
  4. Caching and fallbacks
  5. Design: a support assistant with a p95 of two seconds

Sign in, or sign up if you are new — either way you land on this work.