Research Engineer Cybersecurity RL Environments
Paris-based AI company building frontier models, AI applications, developer tools, and compute infrastructure for enterprise and public-sector deployments.
Maintainer signals as of 9/25/2026
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
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design and implement reinforcement-learning environments for realistic cybersecurity scenarios. You will build synthetic training-data pipelines and the supporting container, sandbox, VM, cloud, and Kubernetes infrastructure. You will evaluate model capabilities, collaborate with security specialists, and write well-tested Python code.
Requirements
- Expertise in offensive and/or defensive cybersecurity, including vulnerability analysis, web, network, or cloud security, secure coding, and SOC
- Software engineering skills
- Python fluency and ability to read C/C++ for vulnerability analysis
- DevOps experience with Docker, Kubernetes, cloud deployments, and sandboxed or simulated environments
- Knowledge of reinforcement-learning techniques and LLM training methodologies, or motivation to develop it
Responsibilities
- Design and implement reinforcement-learning environments for cybersecurity scenarios
- Build pipelines and infrastructure for synthetic cybersecurity training instances
- Conduct experiments and evaluations of model capabilities
- Own container, sandbox, VM, cloud-deployment, and Kubernetes infrastructure
- Translate security expertise into reproducible environments and datasets
- Write efficient Python code and apply testing, code review, and CI/CD practices
Benefits
- Healthcare coverage
- Parental leave
- Retirement plans
- Relocation support
- Wellness programs
- Meal allowances
- Transportation allowances
- Location-specific perks