Lead LLM Engineer: Build Reliable AI Pipelines

Leonar; Paris; Sur place; EUR 90 000 - 150 000; Plein temps

Résumé du poste

Licorne Society is seeking a Lead LLM Engineer to design and evolve our LLM/agent architecture, owning output quality across core use cases such as emails and document analysis. You will build evaluation systems, datasets, and metrics, and drive fast iteration loops from production data.

You will improve retrieval, reasoning, and tool usage while ensuring production reliability and fast execution. You will work directly with product and founders to decide what to build and why, shaping a robust,

Qualifications

• Experience shipping end-to-end LLM pipelines in production.
• Ability to define and track quality metrics for AI outputs.
• Experience building and using real usage datasets for evaluation.
• Familiarity with retrieval, tools, and structured outputs in LLM workflows.

Responsabilités

• Own architecture and output quality across key use cases (emails, documents, etc.).
• Build evaluation datasets and metrics; ensure regression detection.
• Drive fast iteration loops from production data.
• Collaborate with product and founders on what to build and why.

Connaissances

LLM architecture

Production-grade ML systems

Evaluation & metrics

RAG & tools integration

Pipelines over prompts

Telemetry & logs tracing

Debugging complex failures

Speed of iteration

Cross-functional collaboration

Python (FastAPI)

Outils

LangGraph / LangChain

PostHog

Langfuse

Azure OpenAI / LLM APIs

Google Cloud

Postgres

Description du poste

Licorne Society is seeking a Lead LLM Engineer to design and evolve our LLM/agent architecture, owning output quality across core use cases such as emails and document analysis. You will build evaluation systems, datasets, and metrics, and drive fast iteration loops from production data.

You will improve retrieval, reasoning, and tool usage while ensuring production reliability and fast execution. You will work directly with product and founders to decide what to build and why, shaping a robust,