
Research Engineer, Reinforcement Learning Systems
Mistral AI1 day ago
Palo Alto, CA, USASenior
Responsibilities
- Design and build the core Orchestral platform, including its libraries, abstractions, and researcher tooling.
- Develop the rollout engine and capabilities such as long-running tasks and subagents.
- Run Orchestral as a reliable production system for large-scale training and evaluation workloads.
- Improve scheduling, routing, request handling, and data and job flows as platform usage grows.
- Translate researcher workflows and recurring needs into robust shared tooling.
- Improve platform engineering quality through testing, code review, CI/CD, observability, and documentation.
- Contribute to open-source rollout-engine and agent-infrastructure projects when beneficial.
Requirements
- Experience directly building and debugging complex distributed systems at scale, emphasizing reliability and scalability.
- Strong Python skills and sound software-design skills, including testing, code review, and CI/CD.
- Experience constructing systems from the ground up rather than only operating existing systems.
- Track record working in small teams running complex systems at scale, such as in finance, crypto, or ad tech.
- Collaborative, self-starting builder mindset with a product orientation toward users.
- Curiosity about machine learning and reinforcement learning; prior RL experience is not required.
- Hands-on experience with Ray or similar distributed-computing frameworks is a preferred qualification.
- Open-source contributions, particularly to rollout-engine or agent-infrastructure projects such as SLIME, verl, or PrimeRL, are preferred.
- Experience with agentic workflows and environments is preferred.
Benefits
- Benefits may include healthcare coverage, parental leave, retirement plans, relocation support, wellness programs, meal allowances, transportation allowances, and other location-specific perks.
- Benefits vary by country and current details are provided through the company Benefits page.
About Mistral AI
Mistral AI builds foundation language models and full‑stack AI solutions for enterprises, offering APIs, on‑prem deployment, developer tools, and applications. The privately held company, founded in 2023 and headquartered in Paris, partners with organizations in finance, manufacturing, defense, healthcare, and the public sector to co‑create customized systems. It releases open‑source models alongside commercial offerings and makes its models available through major cloud marketplaces.