Model Behavior Architect

About this role

As a Model Behavior Architect at Mistral AI, you will be at the forefront of defining and measuring Large Language Model (LLM) behavior. You will work closely with our Science team to define what 'good' looks like for various tasks, including Reasoning, Audio, Alignment, Tools, and Frontier bets.

Responsibilities

• Interact with models to identify areas for improvement in model behavior
• Gather internal and external feedback on model behavior to scope areas for improvement
• Design and implement evaluation pipelines, data guidelines, data generation, and synthetic testing environments
• Identify and fix edge case behaviors through rigorous testing
• Develop robust evaluation pipelines for model candidates
• Collaborate with AI Scientists

About you

• You have a deep understanding of linguistics, language, and translation, engineering and code behavior, or LLM agents at work, including reasoning and tool use
• You have prior knowledge in training and optimizing model behavior
• You are an expert at building robust evaluations
• You thrive in dynamic and technically complex environments
• You have a track record of delivering innovative, out-of-the-box solutions to address real-world constraints