Reinforcement Learning Systems
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Role details
Tech stack
+11 more
Job description
- Build and own core RL infrastructure: Design, develop, and continuously improve the training systems that support MAI research at scale.
- Drive end-to-end system development: Work across orchestration, environments, training, inference, and evaluation to address emerging research and engineering needs.
- Advance RL research: Investigate training behavior at scale and collaborate with cross-functional research teams to identify opportunities for improving performance and stability.
- Implement new training methods: Translate research ideas into practical algorithms, training recipes, and scalable implementations.
- Optimize performance and efficiency: Profile, benchmark, and optimize RL training and evaluation pipelines to improve throughput, reduce computational overhead, and accelerate experimentation.
- Enable researcher productivity: Develop clean abstractions, well-defined APIs, and comprehensive automated tests that make the system reliable, maintainable, and easy to extend.
- Communicate technical insights: Clearly document engineering decisions, experimental results, performance analyses, and research findings through written reports and technical discussion
- Embody our Culture and Values
Requirements
Reinforcement Learning, Microsoft Product Family, Reinforcement Learning, Use Cases, Artificial Intelligence (AI), Large-Scale Systems, Detail Oriented, Distributed Computing, Debugging Skills, Scientific Research, We are looking for individuals who can contribute to cutting-edge research and help bridge the gap between cutting-edge research and robust, production-grade distributed systems. The ideal candidate has both distributed systems expertise and a scientific mindset and will be able to build complex and scalable systems from the ground up, identify and resolve performance bottlenecks, debug complex, cross-system issues with extremely high attention to detail, and contribute to solving scientific and research challenges. Specifically, they should:
- Excel in programming (especially parallel/concurrent and distributed), software engineering, and system design
- Have experience in large-scale systems, preferably having built some components from scratch.
- Thrive in a highly collaborative, fast-paced environment
- Have a high degree of craftsmanship and pay close attention to details
- Effectively manage multiple responsibilities and can adjust to shifting priorities
A background in machine learning is preferred but not required. In this case, candidates must demonstrate they have an ability to quickly learn the subject, and backgrounds in mathematics, competitive programming, and related domains are a plus.
Microsoft AI, is dedicated to advancing Copilot and other consumer AI products and research. The team is responsible for Copilot, Bing, Edge, and generative AI research. Come be a part of the team shaping the future personal computing., * Bachelorβs Degree in Computer Science or related technical field AND 6+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python
- OR equivalent experience., * Masterβs Degree in Computer Science or related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR Bachelorβs Degree in Computer Science or related technical field AND 12+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python
- OR equivalent experience.
- Experience with generative AI.
- Experience with distributed computing.
- Experience in leading technical projects and supporting architectural decisions with data.
Software Engineering IC5 - The typical base pay range for this role across the U.S. is USD $142,800 - $274,800 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $188,000 - $304,200 per year. Software Engineering IC6 - The typical base pay range for this role across the U.S. is USD $165,600 - $296,400 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $220,800 - $331,200 per year.
About the company
This role is part of Microsoft AI. Our team is a startup-like organization within Microsoft, dedicated to pushing the boundaries of artificial intelligence while maintaining a strong commitment to safety, responsibility, and human values.Our mission is to build AI that amplifies human potential and empowers people around the world. We strive to deliver breakthroughs that advance science, education, productivity, and global well-being.Weβre also fortunate to partner with incredible product teams giving our models the chance to reach billions of users and create immense positive impact. If youβre a brilliant, highly-ambitious and low ego individual, youβll fit right in-come and join us as we work on our next generation of models!
Apply for this position
This job is hosted externally. Click below to view the full posting and apply.
Prepare application
- Draft this with your agent
- Open in Claude
- Open in ChatGPT
Good distractions
Loading talks and stories from around this roleβ¦