Research Scientist, RL for Coding Agents

cursor; New York, San Francisco (NY, CA); On-site; USD 100,000 - 130,000; Full time

Job summary

cursor is hiring a Research Scientist to drive research in reinforcement learning at their New York office. Candidates should have a deep background in RL, be excellent programmers, and be comfortable handling ambiguous tasks with minimal guidance.

The role involves enhancing the understanding of RL, improving data quality for model training, and executing realtime RL for coding agents. This position offers significant scope and autonomy within a small, talented team.

Qualifications

• Deep background in Reinforcement Learning.
• Excellent programming and software engineering skills.
• Ability to handle ambiguous research tasks with minimal guidance.

Responsibilities

• Improve understanding of RL for longer horizon tasks.
• Train graders to enhance performance on coding tasks.
• Improve data points quality for training models.
• Implement realtime RL for coding agents.

Skills

Reinforcement Learning

Programming Skills

Machine Learning Fundamentals

Data Quality Focus

Job description

cursor is hiring a Research Scientist to drive research in reinforcement learning at their New York office. Candidates should have a deep background in RL, be excellent programmers, and be comfortable handling ambiguous tasks with minimal guidance.

The role involves enhancing the understanding of RL, improving data quality for model training, and executing realtime RL for coding agents. This position offers significant scope and autonomy within a small, talented team.