Reinforcement Learning Systems

Microsoft AI•Mountain View, NY
•$142,800 - $331,200•Hybrid

About The Position

Microsoft AI is seeking a Member of Technical Staff to build and operate large-scale reinforcement learning systems for research and products, including trustworthy and capable agents, reasoning models, and conversational assistants. The role bridges research and production-grade distributed systems, developing scalable systems from the ground up, addressing performance bottlenecks and complex cross-system issues, and contributing to scientific and research challenges. The position works across orchestration, environments, training, inference, and evaluation. It involves translating research ideas into practical training methods, investigating training behavior at scale, optimizing pipelines, and creating reliable abstractions, APIs, and tests that support researcher productivity. The role also requires documenting technical decisions, experiments, performance analyses, and research findings. This position is part of Microsoft AI, a startup-like organization within Microsoft focused on advancing artificial intelligence while emphasizing safety, responsibility, and human values. Employees are expected to work from a designated Microsoft office at least four days per 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 jurisdictional variation.

Requirements

  • Bachelor’s degree in Computer Science or a related technical field and 6+ years of technical engineering experience coding in languages such as C, C++, C#, Java, JavaScript, or Python, or equivalent experience.
  • Strong programming, software engineering, and system design skills, particularly in parallel, concurrent, and distributed programming.
  • Experience with large-scale systems; experience building components from scratch is preferred in the role overview.
  • Ability to identify and resolve performance bottlenecks and debug complex cross-system issues with attention to detail.
  • Ability to work collaboratively in a fast-paced environment, manage multiple responsibilities, and adjust to shifting priorities.
  • High craftsmanship and close attention to detail.

Nice To Haves

  • Master’s degree in Computer Science or a related technical field and 8+ years of technical engineering experience coding in relevant languages, or a bachelor’s degree and 12+ years of such experience, or equivalent experience.
  • Experience with generative AI.
  • Experience with distributed computing.
  • Experience leading technical projects and supporting architectural decisions with data.
  • Background in machine learning; it is preferred but not required.
  • Ability to learn machine learning quickly; backgrounds in mathematics, competitive programming, and related domains are a plus.

Responsibilities

  • Build, own, and continuously improve core reinforcement learning training infrastructure supporting research at scale.
  • Develop systems end to end across orchestration, environments, training, inference, and evaluation.
  • Investigate reinforcement learning training behavior at scale and collaborate with research teams to identify performance and stability improvements.
  • Translate research ideas into practical algorithms, training recipes, and scalable implementations.
  • Profile, benchmark, and optimize training and evaluation pipelines to improve throughput, reduce computational overhead, and accelerate experimentation.
  • Develop clean abstractions, well-defined APIs, and comprehensive automated tests to make systems reliable, maintainable, and extensible.
  • Document engineering decisions, experimental results, performance analyses, and research findings, and communicate them through reports and technical discussions.
  • Embody Microsoft’s culture and values.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service