Research Scientist

About the Company

Cursor is building the future of coding. We train frontier coding agents and scale RL on real user data to make them increasingly effective. Our mission is to automate coding through inventive research, design, and engineering.

Responsibilities

• Drive effective RL or mid-training research in a small-team setting
• Own ambiguous research problems end-to-end from hypothesis to implementation
• Improve understanding of RL and handling longer horizon tasks
• Train graders to improve performance on coding tasks with non-verifiable reward
• Improve the quality and difficulty of training datapoints
• Implement realtime RL for coding agents

Requirements

• Deep background in Reinforcement Learning (RL)
• Strong machine learning fundamentals
• Excellent programming and software engineering skills
• Ability to handle ambiguous research tasks with minimal guidance
• Strong focus on data quality and ability to dive into datasets