Senior LLM Engineer: Architect Fast, Reliable AI Workflows

Leonar; Paris; On-site; EUR 90,000 - 125,000; Full time

Job summary

Licorne Society is seeking a Lead LLM Engineer to transform vague user problems into structured AI systems with measurable performance that improve weekly. You will design full pipelines, balance complexity and reliability, and drive eval-driven development across retrieval, prompts, and model behavior.

You will work with LangGraph/LangChain, Langfuse, and product analytics to ensure fast iteration and reduced hallucinations, delivering robust AI-powered workflows within production environments.

Qualifications

• Experience building production AI systems and pipelines.
• Ability to define and measure quality metrics for outputs.
• Experience with evals, datasets, and continuous improvement.

Responsibilities

• Turn vague user problems into structured AI systems.
• Design end-to-end LLM pipelines with measurable performance.
• Build eval frameworks for core use cases and reduce regressions.
• Trace issues across retrieval, prompts, and model behavior.

Skills

LLM systems

Evaluation-driven development

RAG

Tools and agents

Structured outputs

Full pipeline design

Quality metrics

Datasets from real usage

Continuous evaluation

Debugging complex failures

Retrieval prompts

Model behavior tracing

Logs and traces

Tools

LangGraph / LangChain

Langfuse

PostHog

Postgres

Google Cloud

Python (FastAPI)

Job description

Licorne Society is seeking a Lead LLM Engineer to transform vague user problems into structured AI systems with measurable performance that improve weekly. You will design full pipelines, balance complexity and reliability, and drive eval-driven development across retrieval, prompts, and model behavior.

You will work with LangGraph/LangChain, Langfuse, and product analytics to ensure fast iteration and reduced hallucinations, delivering robust AI-powered workflows within production environments.