What does an LLM gateway do, and when do you need one?
Deployment and LLMOps · Pro 1
Short answer
A gateway sits between your apps and model providers and gives one API for many models. It handles routing, fallbacks when a provider fails, retries, rate limits and budgets per team, caching, and central logging of cost and usage, and it keeps provider keys in one place. You need one once several teams or models are in play.
Deeper answer
Tools such as LiteLLM or managed gateways provide this. Routing can also be smart: send easy requests to a cheap model and hard ones to a strong one, as RouteLLM research explored.
The gateway is also where you enforce policy: which models are approved, data rules, and spending caps. Keep it highly available, because it becomes a single point of failure.
What a strong answer covers
- One API across providers
- Routing and fallbacks
- Rate limits and budgets
- Central logging of cost and usage
- Keys and policy in one place
Answer it out loud in the mock interview about 1 min
Follow-ups to expect
- How would you route between a cheap and an expensive model?
- What new risk does a gateway introduce?
Common mistakes
- Hard-coding one provider in every app
- Making the gateway a single point of failure
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?
- What would you capture in traces for an LLM application?
- Why use Docker for an AI application?
- Why use vLLM to serve an open-weight model instead of a simple Hugging Face script?