Lead LLM Engineer

About the role

We are looking for a Lead LLM Engineer to make our AI outputs reliable, fast, and indispensable in real workflows. You will own the end‑to‑end quality of large‑language‑model based features and work closely with product and founders to shape the product roadmap.

Key responsibilities

• Design and evolve the LLM/agent architecture.
• Own output quality across core use cases such as email generation and document analysis.
• Build evaluation systems, including datasets, metrics, and regression detection.
• Drive rapid iteration loops using production data.
• Improve retrieval, reasoning, and tool usage within the system.
• Ensure production reliability (latency, failure modes, fallback mechanisms).
• Collaborate directly with product teams and founders on feature decisions.

Required profile

• Experience building LLM‑powered systems that run in production, not just demos.
• Deep understanding of Retrieval‑Augmented Generation (RAG), tool integration, agents, and structured outputs.
• Ability to design full pipelines rather than isolated prompts.
• Evaluation‑driven mindset: define quality metrics, create real‑usage datasets, and run continuous evaluations.
• Strong debugging skills across retrieval, prompting, and model behavior.
• Fast iteration capability: turn problems into improvements within hours or days using logs and traces.
• Good judgment on when to use agents versus pipelines and how to balance complexity and reliability.

Required skills

• Python (FastAPI)
• PostgreSQL
• Google Cloud Platform
• LangGraph / LangChain
• PostHog (product analytics)
• Langfuse (LLM tracing)
• LLM APIs (Azure OpenAI)