Applied AI, Evaluation Engineer

Mistral AI(13 days ago)

Paris, FranceOnsiteFull TimeMedior$100,910 - $136,540 (estimated)Applied AI

About this role

The Evaluation Engineer on Mistral's Applied AI team designs evaluation methodologies and builds scalable evaluation infrastructure to measure LLM capabilities for enterprise customers. The role defines production readiness across verticals and translates evaluation insights into model and product improvements while interfacing with research, engineering, and customer-facing teams.

View Original Listing

Required Skills

LLM Evaluation
Benchmarking
Evaluation Methodology
Python
APIs
ML Infrastructure
PyTorch
HuggingFace
Customer Engagement
Research Collaboration

About Mistral AI

mistral.ai

Mistral AI builds frontier large language models and an enterprise AI platform that lets companies customize, fine‑tune, and deploy AI assistants, autonomous agents, and multimodal models. Their offering centers on open models, developer APIs, and professional services designed for secure, scalable integration into products and workflows. Mistral combines research-grade model development with tooling for building tailored assistants and autonomous agents for business use cases. They also publish research and consumer-facing apps that showcase their models in action.