We launched recruiters.rip, let your AI apply for you. First month free with code onemonthfree

Research Engineer, Reinforcement Learning Systems

Paris-based AI company building frontier models, AI applications, developer tools, and compute infrastructure for enterprise and public-sector deployments.

Series DRecently funded13 current maintainers13 active leads5 new active leads12 lead step-downs
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.

View jobs by Mistral AI

Skills

Candidate Availability

About the Role

You will help build the agentic platform used to train and evaluate models. You will design the library, tooling, abstractions and rollout engine, shipping new capabilities like long-running tasks and subagents. You will keep training and evaluation workloads reliable at scale, improve scheduling, routing and request handling, and treat researchers as your users. You will own significant pieces end to end, from design to production, and raise engineering quality across the platform.

Requirements

  • Experience building and debugging complex distributed systems at scale with emphasis on reliability and scalability
  • Strong Python skills and solid software-design instincts: testing, code review, CI/CD
  • Builder mindset: constructed systems from the ground up
  • Track record in small teams running complex systems at scale, e.g. finance, crypto or ad tech
  • Curiosity about ML and RL (experience not required)
  • Nice to have: Ray or similar distributed-computing frameworks
  • Nice to have: open-source contributions to SLIME, verl or PrimeRL
  • Nice to have: experience with agentic workflows and environments

Responsibilities

  • Design and build the core of the Orchestral platform: the library, abstractions and tooling
  • Build and evolve the rollout engine, shipping capabilities such as long-running tasks and subagents
  • Run Orchestral as a production system and keep training and evaluation workloads reliable at scale
  • Improve how data and jobs flow through the platform, including scheduling, routing and request handling
  • Understand researchers' workflows and turn recurring needs into robust shared tooling
  • Raise engineering quality through testing, code review, CI/CD, observability and documentation
  • Contribute to open-source rollout-engine and agent-infrastructure projects

Benefits

  • Healthcare coverage
  • Parental leave
  • Retirement plans
  • Relocation support
  • Wellness programs
  • Meal and transportation allowances