Research Engineer, Eval Platform — Scalable AI Evaluation

Mistral in Paris is seeking a Research Engineer for the Eval Platform to build infrastructure that measures model quality, ensuring reproducibility and speed. You'll work with researchers to define evaluation metrics and deliver robust tooling.

You will run large-scale evaluations on GPU clusters (Slurm, Kubernetes, Ray), develop user-friendly APIs and dashboards, and help ensure accuracy by catching noisy results. A Master's or PhD and 4+ years of production ML software experience are required.