Назад
3 дня назад

Research Engineer, Reinforcement Learning Systems (AI)

Формат работы
onsite
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
France/UK/Poland
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Research Engineer, Reinforcement Learning Systems (AI): Building the Orchestral platform for training and evaluating AI models at scale with an accent on distributed systems, rollout engines, reliability, routing, and request handling. Focus on designing researcher-facing tooling, evolving agentic workflows, and operating reliable training and evaluation workloads in production.

Location: Paris; other locations: Warsaw and London, France

Company

Mistral AI builds full-stack AI solutions spanning frontier models, developer tools, applications, and compute for high-stakes industries and public-sector customers.

What you will do

  • Design and build the Orchestral platform library, abstractions, and tooling for training and evaluating models.
  • Build and evolve the rollout engine, including long-running tasks, subagents, and reinforcement-learning capabilities.
  • Run training and evaluation workloads reliably at scale as a production system.
  • Improve scheduling, routing, request handling, and the flow of data and jobs through the platform.
  • Translate researchers’ workflows and recurring needs into robust shared tooling.
  • Improve testing, code review, CI/CD, observability, documentation, and open-source platform projects.

Requirements

  • Direct experience building and debugging complex distributed systems at scale, with emphasis on reliability and scalability.
  • Strong Python skills and sound software-design judgment, including testing, code review, and CI/CD.
  • Experience constructing systems from the ground up rather than only operating existing systems.
  • Experience in small teams running complex systems at scale, for example in finance, crypto, or ad tech.
  • Self-starter mindset, low-ego collaboration, and a product mindset toward users.
  • Curiosity about machine learning and reinforcement learning; prior RL or PyTorch experience is not required.

Nice to have

  • 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.

Culture & Benefits

  • Collaborative, creative, low-ego, and team-spirited environment distributed across Europe, North America, Asia, and the Middle East.
  • Benefits may include healthcare coverage, parental leave, retirement plans, relocation support, wellness programs, and meal and transportation allowances, varying by country.

Будьте осторожны

Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →