About The Position

As a Research Engineer on Mistral’s RL Systems team, you will help build Orchestral, the agentic platform researchers use to train and evaluate models at scale. You will develop the platform’s library, tooling, abstractions, and rollout engine, as well as the systems that run data and jobs reliably at scale. The role includes building capabilities such as long-running tasks, subagents, and reinforcement-learning features, with a focus on resiliency, routing, and request handling. You will own significant work end to end, from design through production, and build for researchers as the platform’s users. This is a software engineering role focused on building a distributed RL system; RL or PyTorch experience is not required, and the role is not focused on infrastructure operations.

Requirements

  • Experience directly building and debugging complex distributed systems at scale, emphasizing reliability and scalability.
  • Strong Python skills and sound software-design instincts.
  • Experience with testing, code review, and CI/CD.
  • A builder mindset and experience constructing systems from the ground up, rather than only operating established systems.
  • A track record in small teams running complex systems at scale.
  • Self-starter who is low-ego and collaborative, with a product mindset toward users.
  • Curiosity about ML and RL and a desire to learn; prior ML or RL experience is not required.

Nice To Haves

  • Hands-on experience with Ray or similar distributed-computing frameworks.
  • Open-source contributions, especially to rollout-engine or agent-infrastructure projects such as SLIME, verl, or PrimeRL.
  • Experience building or working with agentic workflows and environments.

Responsibilities

  • Design and build the core Orchestral platform, including the library, abstractions, and tooling used to train and evaluate models.
  • Build and evolve the rollout engine, including capabilities such as long-running tasks and subagents.
  • Run Orchestral as a production system and keep training and evaluation workloads reliable at scale.
  • Improve the flow of data and jobs through the platform as usage grows, including scheduling, routing, and request handling.
  • Understand researchers’ workflows and turn recurring needs into robust, shared tooling.
  • Improve engineering quality through testing, code review, CI/CD, observability, and documentation.
  • Contribute to open-source rollout-engine and agent-infrastructure projects where beneficial to the platform.
  • Own significant pieces of work end to end, from design to production.

Benefits

  • Healthcare coverage (may vary by country and location).
  • Parental leave (may vary by country and location).
  • Retirement plans (may vary by country and location).
  • Relocation support (may vary by country and location).
  • Wellness programs (may vary by country and location).
  • Meal and transportation allowances (may vary by country and location).
  • Other location-specific perks.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service