Applied AI Engineer

The Opportunity

Take an LLM feature from demo to production: evals, latency budget, cost controls, on-call. A good landing spot for a strong backend engineer moving into AI — the gap they want closed is production LLM ops, learned by doing here, not the model math.

What You'll Be Doing

• Build the eval harness and wire it into CI
• Own latency and cost budgets for the feature

Key Requirements

• Solid backend fundamentals; shipped user-facing systems
• Some exposure to RAG or LLM app patterns

Tech Stack

Python, TypeScript, Postgres, one major model provider.

---

Application Questions

1. Describe an eval you built for a non-deterministic system.
2. How do you think about latency vs. cost when a feature calls a model on the request path?