What would you capture in traces for an LLM application?
Deployment and LLMOps · Pro 1
Short answer
One trace per user request, with a span for each step: retrieval (query, document IDs, scores), each model call (model and version, prompt template version, input and output tokens, latency, cost, parameters), each tool call with arguments and results, and errors. Link user feedback to the trace. Mask personal data and sample if volume is high.
Deeper answer
Tools such as Langfuse or OpenTelemetry-based platforms make this easy. The payoff is debugging: when a user reports a bad answer, you can see exactly what was retrieved and what the model saw.
Traces also feed evals: pick bad or interesting production traces and add them to your test set.
What a strong answer covers
- One trace per request with spans per step
- Retrieval details
- Model, prompt version, tokens, latency, cost
- Tool calls and errors
- Feedback linked; personal data masked
Answer it out loud in the mock interview about 1.5 min
Follow-ups to expect
- How would you link a thumbs-down to the right trace?
- What personal data would you mask?
Common mistakes
- Logging only the final answer
- Storing full personal data in traces forever
Learn it
- 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?
- How would you load test an LLM feature and set a latency budget?
- 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?
- 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?