Lead LLM Engineer

Leonar; Paris; On-site; EUR 90,000 - 140,000; Full time

Job summary

Licorne Society in Paris is looking for a Lead LLM Engineer to design and evolve scalable LLM and agent architectures that solve real workstreams. You will own output quality across critical use cases, from emails to document analysis, and collaborate with product and founders to decide what to build and why.

You will build evaluation systems, datasets from real usage, and run continuous evals to prevent regressions while ensuring reliability and fast iteration.

Qualifications

• Shipping real LLM systems in production.
• Built systems used in production, not demos.
• Design full pipelines, not just prompts.
• Evaluation-driven development with measurable metrics.
• You can define quality metrics and build datasets from real usage.
• Run continuous evals to prevent regressions and debug failures.

Responsibilities

• Design and evolve 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).

Skills

LLM systems

Evaluation-driven development

Debugging complex failures

System architecture

Logs & tracing

Tools

LangChain

LangGraph

Azure OpenAI

PostHog

PostgreSQL

Google Cloud

FastAPI

Job description

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 quality
• Faster 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)