Staff ML Engineer: LLM/RAG Systems (Remote, Equity)

Valoris Fusion; Any-Martin-Rieux; Sur place; EUR 113 000 - 152 000; Plein temps

Avantages offerts par ce poste

Remote-first

Equity

Performance bonus

Learning budget

Unlimited PTO

Résumé du poste

Valoris Fusion is seeking a Staff ML Engineer to build production LLM and retrieval-augmented generation systems for enterprise clients. You will architect AI agents, document intelligence pipelines, and evaluation frameworks to deliver measurable business value.

The role emphasizes real-world impact beyond demos. Responsibilities include designing RAG pipelines, embedding models, and vector store architectures, with ownership of model evaluation and prompt engineering.

Qualifications

• 7+ years in ML/software engineering, with 2+ years building production LLM/RAG systems.
• Deep hands-on experience with LangChain, vector databases (Pinecone or similar), and embedding models.
• Strong Python engineering skills and experience with frameworks like FastAPI.
• Track record shipping AI systems that survived production traffic.
• Familiarity with responsible AI practices: bias auditing, guardrails, evaluation harnesses.
• Experience with MLOps tooling (MLflow or equivalent) for tracking and reproducibility.
• Excellent communication skills for explaining AI system tradeoffs to non-technical stakeholders.

Responsabilités

• Architect and build production RAG pipelines, AI agents, and LLM-powered workflows.
• Design retrieval strategies, chunking approaches, and vector store architectures for scale.
• Own model evaluation, prompt engineering, and fine-tuning where applicable.
• Set technical direction for the AI Practice's engineering standards and tooling.
• Partner with clients on responsible AI practices, bias auditing, and enterprise security requirements.
• Optimize inference cost, latency, and reliability for production LLM systems.
• Mentor ML engineers and review architecture proposals across engagements.

Connaissances

Production LLM

LangChain

Vector databases

Python

FastAPI

MLOps MLflow

Communication

Responsible AI

Outils

FastAPI

MLflow

Pinecone

Description du poste

Valoris Fusion is seeking a Staff ML Engineer to build production LLM and retrieval-augmented generation systems for enterprise clients. You will architect AI agents, document intelligence pipelines, and evaluation frameworks to deliver measurable business value.

The role emphasizes real-world impact beyond demos. Responsibilities include designing RAG pipelines, embedding models, and vector store architectures, with ownership of model evaluation and prompt engineering.