Model Behavior Architect, Safety

Join Mistral, a leading AI solutions provider, as a Model Behavior Architect on the Safety team. In this role, you will define and measure the behavior of large language models, ensuring they meet the highest standards of performance and reliability. You will work closely with the Science team to translate research insights into actionable improvements, shaping the behavior of Mistral's models for complex tasks.

• Interacting with models to identify areas for refinement and optimization.
• Designing and implementing evaluations, data guidelines, and synthetic testing environments.
• Collaborating with AI Scientists to align model behavior with research goals and practical needs.