About Mistral
At Mistral AI, we believe in the power of AI to simplify tasks, save time, and enhance learning and creativity. Our technology is designed to integrate seamlessly into daily working life.
We democratize AI through high-performance, optimized, open-source and cutting-edge models, products and solutions. Our comprehensive AI platform is designed to meet enterprise as well as personal needs. Our offerings include Le Chat, La Plateforme, Mistral Code and Mistral Compute - a suite that brings frontier intelligence to end-users.
We are a dynamic, collaborative team passionate about AI and its potential to transform society. Our diverse workforce thrives in competitive environments and is committed to driving innovation. Our teams are distributed between France, USA, UK, Germany and Singapore. We are creative, low-ego and team-spirited.
Join us to be part of a pioneering company shaping the future of AI. Together, we can make a meaningful impact. See more about our culture on https://mistral.ai/careers.
About the role
As a Model Behavior Architect on the Function Calling team, you are at the forefront of defining and measuring how LLMs use tools, invoke functions, and orchestrate complex agentic workflows.
We are looking for people who have built a career in engineering, machine learning, and large language models and are experts in model evaluation, policy writing, and creating eval pipelines for tool use and function calling. Your role is to work hand-in-hand with our Science team to define what 'good' looks like for function calling—from accurate parameter selection and schema adherence to multi-step tool orchestration, error recovery, and agentic reasoning.
Join us if you are passionate about tackling cutting-edge, open-ended research challenges and transforming your insights into best-in-class models.
What you will do
Interact with models to identify where function calling and tool use behaviour can be improved
Gather internal and external feedback on tool-calling behaviour to scope areas for improvement
Design and implement evals, data guidelines, data generation, and synthetic tool environments and APIs
Identify and fix edge case behaviours, such as malformed arguments, hallucinated functions, and incorrect tool selection—through rigorous testing
Develop robust evaluation pipelines for the function-calling capabilities of our model candidates
Work collaboratively with AI Scientists
About you
You have a deep understanding of either 1) API design, structured outputs, and schema specification (e.g. JSON Schema), 2) engineering and code behavior, 3) LLM agents at work, including reasoning, planning, and multi-step tool use
You have prior knowledge in training and optimising model behaviour
You are an expert at building robust evaluations
You thrive