Model Behavior Architect- Safety

Mistral; Paris; Sur place; EUR 70 000 - 90 000; Plein temps

Résumé du poste

Mistral, based in Paris, is seeking a Model Behavior Architect to define and measure LLM behavior. You will work closely with our Science team to enhance model evaluation and pipeline creation for complex tasks.

The ideal candidate has a robust background in engineering and machine learning, with expertise in model evaluation. Join us to impact AI innovation and tackle research challenges at the forefront of technology.

Qualifications

• Expertise in engineering, machine learning, and large language models.
• Deep understanding of linguistics, language, and translation.
• Prior knowledge in training and optimizing model behavior.

Responsabilités

• Define and measure LLM behavior.
• Work hand-in-hand with the Science team.
• Gather feedback on model behavior for improvement.
• Design and implement evaluations and testing environments.
• Collaborate with AI Scientists.

Connaissances

Engineering

Machine Learning

Large Language Models

Model Evaluation

Policy Writing

Data Generation

Testing Environments

Linguistics

Code Behavior

Description du poste

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.

Mistral AI participates in the E‑Verify program.

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.

• 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 evals, data guidelines, data generation, and synthetic testing environments
• Identify and fix edge case behaviors through rigorous testing
• Develop robust evaluation pipelines for our model candidates
• Work collaboratively with AI Scientists
• You have a deep understanding of either 1) linguistics, language, and translation, 2) engineering and code behavior, 3) LLM agents at work, including reasoning and tool use
• You have prior knowledge in training and optimising model behaviour
• 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