How would you load test an LLM feature and set a latency budget?
Deployment and LLMOps · Pro 2
Short answer
Start from the user experience: for example, first token within one second and a full answer within six seconds at the 95th percentile. Break that budget into parts (retrieval, model, tools). Then simulate realistic traffic with a tool such as Locust or k6, ramping up concurrency, and measure time to first token, latency percentiles, errors and rate limits.
Deeper answer
Use realistic prompts and output lengths, because latency scales with tokens. Test against provider rate limits and your own quotas, and watch for queueing in your service before the model is even called.
Report percentiles, not averages: a 2-second average can hide 10-second tails that users feel. Re-run the test after model, prompt or infrastructure changes.
What a strong answer covers
- Starts from user experience targets
- Splits budget across steps
- Simulates realistic traffic with a load tool
- Measures percentiles and errors
- Checks rate limits and realistic token lengths
Answer it out loud in the mock interview about 1.5 min
Follow-ups to expect
- Why do percentiles matter more than averages?
- What happens when you hit the provider's rate limit?
Common mistakes
- Testing with tiny prompts
- Reporting averages only
Learn it
Latency budgets and load testing
- When would you serve predictions in batch, and when online?
- How would you set up CI/CD for an LLM application?
- What is the difference between data parallelism and model parallelism?
- Why does experiment tracking matter, and what do you record?
- Your model scored well offline but performed badly after launch. What could explain it?
- Explain Kubernetes pods, deployments and services, and why you would use Kubernetes for AI apps.
- What is the KV cache, and why can it cause out-of-memory errors when serving an LLM?
- Your model provider has an outage during peak hours. What should already be in place?
- How do you manage API keys and secrets across environments?
- How do you detect and handle model drift in production?
- A bank wants your AI system but says no data may leave its network. What are the options?
- Why does an LLM reply have a wait before the first word and then a different speed after it?
- What is quantisation, and what are the trade-offs?
- When would you use a semantic cache for an LLM app, and what can go wrong?
- How would you serve an LLM feature as an API for a web app?
- How would you serve a model that is too big for one GPU, and how would you scale it to more users?
- How would you add single sign-on to an enterprise AI assistant?
- How do you version prompts and models so you can roll back safely?
- What would you capture in traces for an LLM application?
- Why use Docker for an AI application?
- What does an LLM gateway do, and when do you need one?
- Why use vLLM to serve an open-weight model instead of a simple Hugging Face script?