Evaluation Engineer, Applied AI
Mistral AI · Paris
Frontier labonsite
At a glance
Highlights
- Build frontier evals that shape Mistral's next flagship models.
- Own benchmarks end-to-end where agents work inside real software.
- Design moonshot evals for work no model can do yet.
What they offer
- healthcare coverage
- parental leave
- retirement plans
- relocation support
- wellness programs
- meal and transportation allowances
Ideal candidate
High-energy, low-ego builder who thrives in ambiguity and learns new industries fast. You love talking to customers and turning messy real-world work into rigorous benchmarks.
Requirements
- 2+ years industry experience in software, AI, or consulting, or a PhD
- Software engineering or research background writing maintainable code
- Experience working directly with customers, industry experts, or cross-functional teams
- Experience building with LLMs with understanding of training, inference, and evaluation
- Strong Python skills and comfort in a large, shared codebase
- Comfort building and cleaning large datasets
- Clear writing and confident presenting in fluent English
Lab profile
About Mistral AI
Provides full-stack AI solutions from frontier models to tools, applications, and compute.
What they build
- Frontier AI models
- Developer tools
- AI applications
Known for
- Full-stack AI development
- Enterprise co-creation and deployment
- Customizable systems that run on customer terms
- Focus on finance, manufacturing, defense, healthcare and public sector
Posted · Last seen