AI Engineer

Engineering builds and runs Vercilio end to end — the chat product, the model-routing layer, billing, and the infrastructure that keeps streaming responses fast and reliable for everyone. We ship in small, autonomous teams and value people who can own a problem from idea to production.

You'll own the layer that makes Vercilio feel smart: how we route between models, how we structure prompts and tools, and how we measure whether the output is actually good.

This role sits between research and product — you'll turn frontier model capabilities into features people rely on every day.

• Build and tune our auto-router so every message gets the best-fit model.
• Design prompting, tool-use, and retrieval patterns that improve answer quality.
• Create evaluations that catch regressions before users do.
• Integrate new models and capabilities as they're released.

• Hands-on experience building with LLM APIs in production.
• A rigorous, measurement-driven approach to quality.
• Strong software fundamentals — this is an engineering role, not just prompting.
• Curiosity about where models are heading and what they can't yet do.