How would you serve an LLM feature as an API for a web app?
Deployment and LLMOps · Intermediate 3
Short answer
Put a backend service, for example FastAPI, between the browser and the model provider so keys stay secret and you can add auth, rate limits and logging. Stream tokens to the client with server-sent events so users see text at once, set timeouts and retries, validate inputs and outputs, and run it with multiple workers behind a load balancer.
Deeper answer
Calls to model APIs are slow and I/O-bound, so async handlers or enough workers matter. Handle client disconnects so you stop paying for tokens nobody reads. Return clear errors when the provider is down, and consider a fallback model.
Log request IDs, latency, token counts and cost per request from day one; they are what you will need when something goes wrong.
What a strong answer covers
- Backend between browser and provider keeps keys secret
- Auth, rate limits and logging
- Streams tokens to the client
- Timeouts, retries and fallbacks
- Scales with workers or async
Answer it out loud in the mock interview about 1.5 min
Follow-ups to expect
- Why not call the model API directly from the browser?
- How do you handle the provider being down?
Common mistakes
- Exposing API keys in the frontend
- No timeouts on model calls
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 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?