At a Glance
- Tasks: Define and measure how AI models interact with tools and orchestrate workflows.
- Company: Join Mistral, a dynamic team passionate about transforming society with AI.
- Benefits: Comprehensive benefits package including healthcare, wellness programs, and work-life balance support.
- Other info: Thriving in a collaborative, innovative environment with global teams.
- Why this job: Make a real impact on AI capabilities and solve complex real-world problems.
- Qualifications: Deep understanding of API design and experience with LLM agents or model behaviour.
The predicted salary is between 60000 - 80000 £ per year.
About Mistral
Mistral provides full-stack AI solutions: from frontier models to developer tools, applications, and compute. We partner with enterprises tackling the hardest problems—across high-stakes industries like finance, manufacturing, defense, healthcare, and the public sector—co-creating customized AI systems that they can run on their terms. 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 Europe, North America, Asia and the Middle East. We are creative, low-ego and team-spirited.
The Role
As a Model Behaviour Architect on the General Agents team, you will define and measure how large language models interact with tools, invoke functions, and orchestrate complex workflows. This role exists to ensure our models excel at accurate, reliable, and intelligent tool use, from precise parameter selection to multi-step orchestration and error recovery. You will collaborate closely with our Science team to shape what "good" looks like for function calling, turning research insights into best-in-class model behaviour. Your work will directly impact the capabilities of Mistral’s models, enabling them to solve real-world problems with greater autonomy and precision.
What You Will Do
- Interact with models to identify opportunities for improving function calling and tool use behaviour.
- Gather internal and external feedback to scope and prioritise areas for enhancement.
- Design and implement evaluations, data guidelines, and synthetic tool environments and APIs.
- Address edge cases such as malformed arguments, hallucinated functions, and incorrect tool selection through rigorous testing.
- Develop robust evaluation pipelines to assess the function-calling capabilities of model candidates.
- Collaborate with AI Scientists to align model behaviour with research insights and real-world needs.
What We're Looking For
- Deep understanding of API design, structured outputs, and schema specification (e.g., JSON Schema), or expertise in engineering and code behaviour, or experience with LLM agents, including reasoning, planning, and multi-step tool use.
- Prior knowledge in training and optimising model behaviour for real-world applications.
- Expertise in building robust, scalable evaluation frameworks for AI systems.
- Ability to thrive in dynamic, technically complex environments and deliver innovative solutions.
- Track record of solving open-ended challenges with creative, out-of-the-box approaches.
What We Offer
We offer a comprehensive benefits package designed to support your well-being, growth, and work-life balance. Benefits vary by country and may include healthcare coverage, parental leave, retirement plans, relocation support, wellness programs, meal and transportation allowances, and other location-specific perks. For the most up-to-date details on benefits available in your location, please refer to our Benefits page.
Model Behaviour Architect, General Agents employer: Mistral AI
Mistral AI is an exceptional employer, offering a dynamic work environment in Greater London where innovation meets collaboration. With competitive salaries, equity options, and comprehensive health benefits, we prioritise employee well-being and growth, fostering a culture that encourages continuous learning and development in the exciting field of multilingual AI research.
