Model Behavior Architect- Safety

Mistral AI|29 Sep 2025

fulltimeonsite

Before you apply

Listed location: Paris

Work arrangement: onsite. A remote label does not confirm worldwide eligibility or visa sponsorship.

Read the employer’s description for qualifications, compensation and work eligibility. Confirm the position is still open on the application page.

Job description supplied by Mistral AI; category and skill labels may be inferred. How our listings work · Report a problem

Job Description

About the role

As a Model Behavior Architect, you are at the forefront of defining and measuring LLM behaviour.

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 complicated tasks. Your role is to work hand-in-hand with our Science team to define what ‘good’ looks like for Reasoning, Audio, Alignment, Tools, and all Frontier bets.

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

Skills mentioned

LLM

Frequently asked questions

Is the Model Behavior Architect- Safety position at Mistral AI remote?

The Model Behavior Architect- Safety role at Mistral AI does not have a confirmed remote arrangement in our data. Check the employer description for its work location.