LLM Systems Engineer: Scale Fast, Trustworthy AI

Leonar; Paris; Sur place; EUR 100 000 - 150 000; Plein temps

Résumé du poste

Leonar is building an AI coworker for legal and professional services in Paris. The role focuses on turning vague user problems into structured AI systems with measurable performance that improve every week.

You will own the production AI system, ensure reliability, and drive fast iteration loops. The candidate should excel in architecture design, evaluation, and operating large-scale AI workflows within a multidisciplinary team.

Qualifications

• Shipping real LLM systems.
• Evaluation-driven development approach to building AI.
• Ability to debug complex failures across systems.
• Fast iteration against production data.
• Strong technical judgment to guide architecture and tradeoffs.

Responsabilités

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

Connaissances

Shipping

Evaluation-driven development

Debugging failures

Speed of iteration

Technical judgment

Outils

LangGraph

LangChain

PostgreSQL

FastAPI

GCP

Azure OpenAI

Multi-provider APIs

Description du poste

Leonar is building an AI coworker for legal and professional services in Paris. The role focuses on turning vague user problems into structured AI systems with measurable performance that improve every week.

You will own the production AI system, ensure reliability, and drive fast iteration loops. The candidate should excel in architecture design, evaluation, and operating large-scale AI workflows within a multidisciplinary team.