- Microsoftcorporation
- London, Greater London
- 6 days ago
Reinforcement Learning for Frontier AI Models.
Before you go
Before you leave us, sign up for our email alerts
We don't do job spam, just the best digital jobs delivered straight to your inbox.
Reinforcement Learning for Frontier AI Models: our view in 3 lines...
- The Role:This role is for an engineer or scientist who works on reinforcement learning methods that improve large language models before they are released to users.
- The Person:The person will drive curation of RL environments and training data, build evaluations of model capabilities, design experiment plans, and apply RL techniques to improve models.
- Requirements:The ideal candidate has experience with reinforcement learning and LLMs, 4+ years of software engineering experience, and a Bachelor's degree in Computer Science, Machine Learning, or Mathematics.
About the role
Overview
At Microsoft AI, we are on a mission to develop the most cutting-edge algorithms for post-training large language models (LLMs) and ship those models to millions of users every day.
The RL team at Microsoft AI is responsible for large-scale reinforcement learning and improving our pre-trained models to advance their capabilities in reasoning, instruction following, agentic coding, and agentic knowledge work.
As a Member of Technical Staff – Large Scale Reinforcement Learning, you will contribute across all stages of the RL process: driving the curation of high-quality RL environments and training data, building evaluations that measure both core model capabilities and real-world performance, and applying advanced RL techniques to develop and improve our RL recipe. We work at the bleeding edge, leveraging the most powerful pre-trained models, algorithms, and sources of feedback available to us. We are an interdisciplinary team of engineers and scientists, learning from each other and collaborating closely to build the best possible models.
We are looking for outstanding individuals excited about contributing to the next generation of models that will transform the field. We are looking for candidates who:
- Are passionate about advancing the state of the art in reinforcement learning;
- Have experience with RL algorithms, RL environment creation, or using real-world data and feedback to improve models;
- Will thrive in a highly collaborative, fast-paced environment;
- Have a high degree of craftsmanship and pay close attention to detail, consistently striving for engineering excellence;
- Are willing to contribute meaningfully as individuals and take end-to-end ownership of projects.
Microsoft AI - 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.
Responsibilities
- Work on our data collection, evaluation, and reinforcement learning methods for models.
- Design hypotheses and experiment plans for rapidly iterating on model performance.
- Embody our Culture and Values.
Required Qualifications
- Bachelor's degree in Computer Science, Machine Learning, Mathematics, or a related technical field, or equivalent experience.
- 4+ years of software engineering experience.
- Experience with reinforcement learning and LLMs.
Preferred Qualifications
- Experience building and scaling large AI systems.
- Experience applying reinforcement learning to AI models and agents.
- Strong collaboration and communication skills
Software Engineering IC5 - The typical base pay range for this role across United Kingdom is £ 91,800 - £ 137,600 per year. Software Engineering IC5 - The typical base pay range for this role across Switzerland is 183,800 CHF - 275,800 CHF per year.
Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here:
https://careers.microsoft.com/us/en/us-corporate-pay
This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.

