Member of Technical Staff, AI - Reinforcement Systems

Microsoft

| London, United Kingdom (On Site) | Full Time | 7 months ago

Apply Now

Job Summary

This role involves building advanced reinforcement learning systems at Microsoft AI, focusing on creating trustworthy, autonomous agents. Responsibilities include collaborating with research teams to improve reinforcement learning algorithms for LLMs, developing core systems for scaling reinforcement learning to diverse environments, and ensuring high-quality software engineering practices. The ideal candidate excels in programming (parallel/concurrent), software engineering, API design, and large-scale system development. Experience with large-scale systems and a demonstrated interest in reinforcement learning are essential. The role demands collaboration, attention to detail, and the ability to manage multiple responsibilities in a fast-paced setting.

Must Have

Expert in parallel/concurrent programming
Strong software engineering & API design skills
Large-scale system experience
Reinforcement learning knowledge
Collaboration & problem-solving skills

Good to Have

Machine learning research background
Large-scale distributed AI systems experience

Job Description

Help build the world’s most advanced reinforcement learning systems at Microsoft AI.

We're on a mission to create trustworthy agents capable of autonomous action and decision-making on behalf of our users. As part of our team, you’ll help advance state-of-the-art model capabilities by contributing to core systems, infrastructure, and research.

We are looking for distributed systems experts with a scientific mindset. The ideal candidate will be able to build complex systems from the ground up, discover and diagnose causes of suboptimal performance, and contribute to solving scientific and research challenges. Specifically, they should:

Excel in programming (especially parallel/concurrent), software engineering, and API 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
Be motivated by training capable and safe AI agents and shipping them into the hands of millions of users

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’s mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

Responsibilities

Collaborate with research teams to advance state-of-the-art algorithms for reinforcement learning in LLMs
Develop the core systems for adapting reinforcement learning to unprecedented scales and heterogeneous environments.
Embody our of collaboration, innovation, and excellence.

Qualifications

Required Qualifications:

Bachelor's Degree in Computer Science, Software Engineering, Computer Engineering, Machine Learning, Mathematics, or related STEM fields and experience in coding in languages including, but not limited to, C, C , C#, Rust, Java, or Python
Experience with large-scale software systems and infrastructure.
Demonstrated interest in reinforcement learning, language modelling, generative modelling, or related domains.
Ability to work collaboratively in a fast-paced, innovative environment.

Preferred Qualifications: