Model Behavior Architect- Multilingual

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

Avantages offerts par ce poste

Competitive cash salary and equity

Daily lunch vouchers

Discounted gym access

Monthly transportation contribution

Full health insurance

Generous parental leave policy

Visa sponsorship

Résumé du poste

Mistral is looking for a Model Behaviour Architect in Paris to work with the Multilingual team. You will enhance model behaviour across languages, defining what ‘good’ looks like while collaborating with the Science team. Your expertise in engineering and machine learning will be crucial in addressing complex multilingual challenges.

The ideal candidate will possess strong skills in model evaluation and multilingual NLP, ensuring robust cross-language testing. The role offers a competitive salary, health insurance, and various employee benefits, including lunch vouchers and gym access.

Qualifications

• Expert at building robust evaluations.
• Strong understanding of linguistics, language, and translation.
• Proven track record of delivering innovative solutions.

Responsabilités

• Interact with models to improve multilingual behaviour.
• Define high-quality behaviour per language.
• Develop evaluation pipelines for model candidates.

Connaissances

Expertise in model evaluation

Understanding of linguistics or multilingual NLP

Innovation in problem-solving

Cross-language testing experience

Description du poste

About the role

As a Model Behaviour Architect in the Multilingual team, you define and measure what good model behaviour looks like across languages, not just in English. 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 building eval pipelines for complex tasks. Your role is to work hand in hand with our Science team to define what “good” means for multilingual behaviour: language adherence, naturalness, cultural alignment, and consistent capability across the languages in which our models are deployed. Join us if you are passionate about tackling cutting‑edge, open‑ended research challenges and transforming your insights into best‑in‑class models that work for users in every language and culture they belong to.

What you will do

• Interact with models across languages to identify where multilingual behaviour can be improved
• Gather internal and external feedback to scope areas for improvement
• Define what high‑quality behavior means per language
• Design and implement evals, data guidelines, data generation, and synthetic testing environments for multilingual settings
• Shape how models reflect the cultural context of the users and regions they serve
• Identify and fix edge‑case behaviors through rigorous cross‑language testing
• Develop robust evaluation pipelines for model candidates
• Work collaboratively with AI Scientists

About you

• You are an expert at building robust evaluations
• You have a strong understanding of at least one of: linguistics, language, and translation; LLM agents at work, including reasoning and tool use. Depth in linguistics or multilingual NLP is strongly preferred
• 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

Benefits

• Competitive cash salary and equity
• Daily lunch vouchers: Swile meal vouchers with 10,83€ per worked day, incl 60% offered by company
• Sport: Enjoy discounted access to gyms and fitness studios through EGYM Wellpass partnership
• Transportation: Monthly contribution to a mobility pass via Swile
• Health: Full health insurance for you and your family
• Parental: Generous parental leave policy
• Visa sponsorship