Reinforcement Learning Systems

Microsoft AI • Redmond, WA

14h • $142,800 - $331,200

About The Position

Microsoft AI is seeking a Member of Technical Staff to build, operate, and improve large-scale reinforcement learning systems used to train capable and trustworthy agents, reasoning models, and conversational assistants. The role bridges cutting-edge research and production-grade distributed systems, contributing to research challenges as well as the design and implementation of scalable systems. The work spans orchestration, environments, training, inference, and evaluation, with an emphasis on system performance, reliability, and researcher productivity.

This position is part of Microsoft AI, a startup-like organization within Microsoft focused on advancing artificial intelligence while prioritizing safety, responsibility, and human values. Microsoft AI works on Copilot and other consumer AI products and research, in partnership with product teams whose models reach billions of users. Employees who live within 50 miles of a designated U.S. Microsoft office, or within the specified country-dependent distance outside the U.S., are expected to work from that office at least four days a week, 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 including C, C++, C#, Java, JavaScript, or Python, or equivalent experience.
• Strong programming, software engineering, and system design abilities, especially in parallel, concurrent, and distributed programming.
• Experience with large-scale systems; experience building system components from scratch is preferred in the role overview.
• Ability to build complex scalable systems, identify and resolve performance bottlenecks, and debug complex cross-system issues with high attention to detail.
• Ability to contribute to scientific and research challenges and to quickly learn machine learning concepts if lacking a machine learning background.
• Ability to thrive in a collaborative, fast-paced environment, manage multiple responsibilities, and adapt to shifting priorities.
• High degree of craftsmanship and 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 the listed or comparable languages, or equivalent experience.
• Bachelor's degree in Computer Science or a related technical field and 12+ years of technical engineering experience coding in the listed or comparable languages, 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.
• Background in mathematics, competitive programming, or related domains.

Responsibilities

• Build, own, and continuously improve core reinforcement learning infrastructure and training systems supporting Microsoft AI research at scale.
• Drive end-to-end system development across orchestration, environments, training, inference, and evaluation.
• Investigate training behavior at scale and collaborate with research teams to identify ways to improve performance and stability.
• Translate research ideas into practical algorithms, training recipes, and scalable implementations.
• Profile, benchmark, and optimize reinforcement learning 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 easy to extend.
• Document engineering decisions, experimental results, performance analyses, and research findings in written reports and technical discussions.
• Embody Microsoft's culture and values.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior