LLM Systems Engineer — Build Reliable Production AI

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. We are not looking for someone to “use GPT APIs.” We are looking for someone to 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 key use cases, build evaluation systems, drive fast iteration loops from production data, improve retrieval and tool

Qualifications

• Shipping real LLM systems
• Evaluation-driven development
• Debugging complex failures
• Speed of iteration and 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).

Skills

LLM Systems

Evaluation-driven dev

Debugging

Performance optimization

Technical judgment

Tools

LangGraph

LangChain

PostHog

Langfuse

GCP

Job description

Leonar is building the AI coworker for legal and professional services — automating emails, document analysis, and complex workflows in high-stakes industries. We are not looking for someone to “use GPT APIs.” We are looking for someone to 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 key use cases, build evaluation systems, drive fast iteration loops from production data, improve retrieval and tool