Lead LLM Engineer — Production AI Pipelines

Licorne Society; Paris; Sur place; EUR 90 000 - 130 000; Plein temps

Résumé du poste

Licorne Society is partnering with a growing AI startup to hire a Lead LLM Engineer who can make AI outputs reliable, fast, and indispensable in real workflows. You will own the architecture and ensure quality across key use cases.

You will design production-grade pipelines, build evaluation systems, and drive fast iterations from real data. Collaboration with product and founders will shape what to build and why.

Qualifications

• You’ve built systems used in production (not demos).
• You understand RAG, tools, agents, structured outputs.
• You can design full pipelines, not just prompts.
• You know how to define quality metrics and create datasets from real usage.
• You run continuous evals to prevent regressions.
• You can trace issues across retrieval, prompts, and model behavior.
• You move quickly from problem to solution using logs and data.

Responsabilités

• Design and evolve LLM/agent architecture.
• Own output quality across key use cases.
• Build evaluation systems (datasets, metrics).
• Drive fast iteration from production data.
• Improve retrieval, reasoning, and tool usage.
• Ensure production reliability (latency, failure modes, fallback).
• Collaborate with product and founders on what to build and why.

Connaissances

Production systems

RAG & tools

Pipelines design

Quality metrics

Dataset creation

Continuous evals

Debugging failures

Tracing & logs

Fast iteration

Decision making

Outils

Python

FastAPI

PostgreSQL

Google Cloud

LangGraph

LangChain

PostHog

Langfuse

Azure OpenAI

Description du poste

Licorne Society is partnering with a growing AI startup to hire a Lead LLM Engineer who can make AI outputs reliable, fast, and indispensable in real workflows. You will own the architecture and ensure quality across key use cases.

You will design production-grade pipelines, build evaluation systems, and drive fast iterations from real data. Collaboration with product and founders will shape what to build and why.