Production LLM Engineer — Reliable AI Systems

Leonar; Paris; On-site; EUR 90,000 - 130,000; Full time

Job summary

Leonar is building the AI coworker for legal and professional services, automating emails, document analysis, and complex workflows in high-stakes industries. You will own and scale a production AI system that users rely on daily.

You will design and evolve our LLM/agent architecture, own output quality across use cases, build evaluation systems, and drive fast iteration through real-prod data. You will also improve retrieval, reasoning, and tool usage while ensuring production reliability and

Qualifications

• Shipping real LLM systems
• Evaluation-driven development
• Debugging complex failures
• Speed of iteration
• Strong technical judgment

Responsibilities

• 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, fallbacks).
• Work directly with product and founders on what to build and why.

Skills

Shipping Real LLM Systems

Evaluation-Driven Development

Debugging Complex Failures

Speed of Iteration

Strong Technical Judgment

Tools

LangGraph

LangChain

PostHog

Langfuse

Azure OpenAI

Job description

Leonar is building the AI coworker for legal and professional services, automating emails, document analysis, and complex workflows in high-stakes industries. You will own and scale a production AI system that users rely on daily.

You will design and evolve our LLM/agent architecture, own output quality across use cases, build evaluation systems, and drive fast iteration through real-prod data. You will also improve retrieval, reasoning, and tool usage while ensuring production reliability and