Research Engineer - Tokenizer & Protocols
Mistral AIVisit Mistral AI website
Paris-based AI company building frontier models, AI applications, developer tools, and compute infrastructure for enterprise and public-sector deployments.
Paris, France
About Mistral AI
Mistral AI develops open-weight and commercial language models and provides a full-stack AI platform spanning agents, application development, custom-model training, APIs, and AI cloud infrastructure.
Skills
Candidate Availability
About the Role
You will help own the formats and tokenizers that training, evaluation and production rely on, plus the tooling around them. You will design, build and maintain core tokenization and model-interface libraries, evolve formats as models and use cases change, and turn research needs into robust shared tooling across pretraining, post-training and deployment.
Requirements
- Strong software engineering background with excellent Python
- Excellent understanding of tokenizers: BPE, special tokens, chat templates, tokenizer training
- Experience building production-grade libraries used by many people
- Attention to detail
- Good knowledge of how LLMs are trained and served
- Clear communication and collaborative mindset
Responsibilities
- Design, build and maintain core libraries for tokenization and model interfaces
- Evolve formats and tokenizers as models and use cases change
- Turn research needs into robust, shared tooling
Benefits
- Healthcare coverage
- Parental leave
- Retirement plans
- Relocation support
- Wellness programs
- Meal and transportation allowances
