
Reinforcement Learning for Frontier AI Models
AI
Microsoft AI is seeking a Member of Technical Staff for its Large Scale Reinforcement Learning team in London to advance post-training of frontier LLMs. The role spans RL environment curation, evaluation design, and applying advanced RL techniques to improve model reasoning, instruction following, and agentic capabilities. Candidates need 4+ years of software engineering experience plus reinforcement learning and LLM expertise.
What you'll do
- Work on 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
What you need
Must-have
Reinforcement LearningLarge Language ModelsSoftware Engineering
Nice-to-have
Large AI systemsAI agents
Soft skills
CollaborationCommunicationAttention to detailCraftsmanshipEnd-to-end ownershipLow ego
Reinforcement LearningLLMsAIMachine LearningSoftware EngineeringMicrosoft AILondonFull-timeOn-site