Назад
1 день назад

Reinforcement Learning for Frontier AI Models (AI)

119 800 - 234 700$
Формат работы
hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
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
Reinforcement Learning for Frontier AI Models (AI/LLMs): Developing large-scale reinforcement learning methods, environments, training data, and evaluations to improve frontier language models in reasoning, instruction following, agentic coding, and knowledge work with an accent on advanced RL techniques and real-world feedback. Focus on designing experiments, scaling AI systems, and measuring model performance across core capabilities and practical applications.

Location: Mountain View, United States. Employees living within 50 miles of the designated U.S. office are expected to work from the office at least four days per week.

Salary: USD $119,800–$234,700 per year for Software Engineering IC4 across the U.S.; higher ranges apply to IC5 and specified San Francisco Bay Area and New York City locations.

Company

Microsoft AI develops advanced artificial intelligence models and products designed to amplify human potential and serve users worldwide.

What you will do

  • Develop data collection, evaluation, and reinforcement learning methods for large language models.
  • Curate high-quality reinforcement learning environments and training data.
  • Build evaluations for core model capabilities and real-world performance.
  • Design hypotheses and experiment plans to iterate rapidly on model performance.
  • Apply advanced reinforcement learning techniques to improve reasoning, instruction following, agentic coding, and agentic knowledge work.
  • Collaborate with interdisciplinary engineers and scientists while taking end-to-end ownership of projects.

Requirements

  • Bachelor's degree in Computer Science, Machine Learning, Mathematics, or a related technical field, or equivalent experience.
  • 4+ years of software engineering experience.
  • Experience with reinforcement learning and large language models.
  • Passion for advancing reinforcement learning and strong attention to engineering quality.
  • Ability to work from the designated Microsoft office at least four days per week when living within the applicable distance threshold.

Nice to have

  • Experience building and scaling large AI systems.
  • Experience applying reinforcement learning to AI models and agents.
  • Strong collaboration and communication skills.

Culture & Benefits

  • Interdisciplinary collaboration between engineers and scientists.
  • Opportunity to work on models serving millions or billions of users.
  • Benefits and additional compensation may be available depending on the role.
  • Microsoft provides reasonable accommodations during the application process.

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 →