Member of Technical Staff, AI - Reinforcement Learning Systems

Help build cutting-edge reinforcement learning systems at Microsoft AI, creating trustworthy agents for autonomous action and decision-making. Contribute to core systems, infrastructure, and research, advancing state-of-the-art model capabilities. Collaborate with research teams on reinforcement learning algorithms for LLMs and develop core systems for adapting reinforcement learning to large scales and diverse environments. This role requires expertise in parallel/concurrent programming, software engineering, API design, and large-scale systems. A background in machine learning is preferred but not mandatory; strong mathematical or competitive programming skills are valuable alternatives. The position is based in Mountain View, CA or Redmond, WA, requiring in-office presence 3 days a week.