Reinforcement Learning for Frontier AI Models

Microsoft AI•Mountain View, NY
•$119,800 - $304,200•Hybrid

About The Position

At Microsoft AI, the RL team develops large-scale reinforcement learning methods to improve pre-trained large language models and advance their reasoning, instruction following, agentic coding, and agentic knowledge-work capabilities. The Member of Technical Staff – Large Scale Reinforcement Learning contributes across the RL process, including curating high-quality environments and training data, building evaluations of model capabilities and real-world performance, and applying advanced RL techniques to improve the team’s training recipe. The team works with advanced models, algorithms, and sources of feedback in a collaborative, fast-paced, interdisciplinary environment. Employees are expected to work from a designated Microsoft office at least four days a week if they live within 50 miles of that location in the U.S. or 25 miles outside the U.S., subject to local law and jurisdiction-specific variation.

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 the state of the art in reinforcement learning.
  • Experience with RL algorithms, RL environment creation, or using real-world data and feedback to improve models.
  • Ability to thrive in a highly collaborative, fast-paced environment.
  • High degree of craftsmanship and attention to detail, with a commitment to engineering excellence.

Nice To Haves

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

Responsibilities

  • Work on data collection, evaluation, and reinforcement learning methods for models.
  • Design hypotheses and experiment plans to rapidly iterate on model performance.
  • Embody Microsoft’s Culture and Values.
  • Contribute across the RL process, including curating environments and training data, evaluating model capabilities and real-world performance, and applying advanced RL techniques to improve the RL recipe.
  • Take end-to-end ownership of projects and contribute as an individual.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service