Model Behavior Architect

About the role

As a Model Behavior Architect, you’re at the forefront of shaping LLM system behaviour to align to Mistral’s values. 

We’re looking for people who have experience with Literature and Translation, who are experts in model evaluation, prompt engineering, and policy writing. Your role would include helping our Science team create AI systems that respond with good generations across diverse scenarios.

Join us if you are passionate about tackling cutting-edge, open-ended research challenges and transforming your findings into best-in-class model responses.

• Interact with models to identify where model behavior can be improved
• Gather internal and external feedback on model behavior to scope areas for improvement
• Design and implement subtle prompting strategies, data generation, and evaluation pipelines that steer better model responses
• Identify and fix edge case behaviors through rigorous testing of your data generation pipelines
• Develop evaluations of language model behaviors
• Work collaboratively with AI Scientists on related teams like Alignment, RAG, Multimodal, Audio, and Code Generation

• You have a deep understanding of the humanities; whether it’s literature, language, anthropology, philosophy, political science, film, etc.
• You have prior knowledge in training and optimising model behaviour and building evaluations
• You are keen to dive into prompt generations and unit tests
• 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

About Mistral 

At Mistral AI, our mission is to make AI ubiquitous and open. We are passionate about bridging the gap between technology and businesses of all sizes. We are a leading innovator in the field of open-source large language models.

Our advanced LLM solutions can be seamlessly deployed on any cloud, allowing for optimized integration and robust performance. Developers are using our API via la Plateforme to build incredible AI-first applications powered by our models that can understand and generate natural language text and code. We are multilingual at our core. We released le Chat, as a demonstrator of our models.

We are a tight-knit, nimble team dedicated to bringing our cutting-edge AI technology to the world. Our teams are distributed between France, UK and USA. We are creative, low-ego, team-spirited, and have been passionate about AI for years. We hire people who thrive in competitive environments, because they find them more fun to work in. We hire passionate women and men from all over the world.

Mistral AI participates in the E-Verify program