Lead LLM Engineer

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 a été missionné par une startup IA en pleine croissance pour les aider à trouver leur Lead LLM Engineer.

What You Will Own

You will be responsible for one thing:

Make our AI outputs reliable, fast, and indispensable in real workflows.

Concretely

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

What This Role Is Really About

Most teams fail because:

• they don't know what “good output” means
• they don't have evals
• they iterate randomly
• they overuse agents

Your job is to fix that.

You Will Turn

• vague user problems
• into structured AI systems
• with measurable performance
• that improve every week

What You Need To Be Excellent At

• Shipping real LLM systems
• You’ve built systems used in production (not demos)
• You understand RAG, tools, agents, structured outputs
• You can design full pipelines, not just prompts
• Evaluation-driven development
• You know how to define quality metrics
• You build datasets from real usage
• You run continuous evals to prevent regressions
• Debugging complex failures
• You can trace issues across:
  • retrieval
  • prompts
  • model behavior
• You don't guess — you isolate and fix
• Speed of iteration
• You move from problem improvement in hours or days, not weeks
• You use logs, traces, and data — not intuition alone
• Strong judgment
• You know when to:
  • use an agent vs a pipeline
  • add complexity vs simplify
• You optimize for reliability and user value, not novelty

What We Don't Care About

• Number of years of experience
• Whether you’ve used a specific framework
• Fancy research credentials

If you can build, debug, and improve real systems, you’re a fit.

What Success Looks Like (first 90 Days)

• Clear eval framework for core use cases
• Measurable improvement in output qualityFaster iteration cycles across the team
• Reduced hallucinations / failures
• Stronger system architecture decisions

Stack (context, Not Requirements)

• Python (FastAPI)
• Postgres
• Google Cloud
• LangGraph / LangChain (evolving)
• PostHog (product analytics)
• Langfuse (LLM traces)
• LLM APIs (Azure OpenAI)