Lead LLM Engineer

Leonar; Paris; Sur place; EUR 90 000 - 140 000; Plein temps

Résumé du poste

Licorne Society partners with a fast-growing AI startup to hire a Lead LLM Engineer. You will design and evolve our LLM/agent architecture and own output quality across core use cases.

This role requires building production-grade pipelines, evaluation frameworks, and fast iteration from real data, with focus on reliability, latency, and meaningful user value. You’ll collaborate with product and founders on what to build and why.

Qualifications

• Experience building real LLM systems in production.
• Understanding of RAG, tools, and structured outputs.
• Ability to design full pipelines, not just prompts.
• Strong evaluation mindset and measurable outcomes.

Responsabilités

• Design and evolve LLM/agent architecture.
• Own output quality across core use cases (emails, docs, etc.).
• Build evaluation datasets and metrics.
• Drive rapid iteration loops from production data.
• Improve retrieval, reasoning, and tool usage.
• Ensure production reliability (latency, failures, fallbacks).
• Collaborate with product and founders on roadmap.

Connaissances

LLM systems

Production debugging

Evaluation-driven development

Pipelines design

Retrieval & tools

Strong judgment

Speed of iteration

Data-driven decision making

Incident analysis

Outils

LangGraph / LangChain

Langfuse

LangChain

Azure OpenAI

Python (FastAPI)

Postgres

Google Cloud

PostHog

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)