Software Engineer - RL Data

As a Software Engineer on the RL Data team, you'll design and build tools for researchers and external contributors to create, review, submit, and monitor environments and tasks behind Cursor's reinforcement-learning runs.

This is a full-stack product-engineering role embedded in a research team. You'll own the review and acceptance experience end-to-end, from rollout and transcript inspection to workflows that move a submission into training.

Your work will significantly shorten the loop from a task idea or data sources to trusted training data.

Responsibilities

• Create fast, trustworthy workflows for vendors and the research team to interact effectively with each other.
• Build review tools for inspecting and comparing rollouts, transcripts, grader outputs, and other signals of task quality.
• Develop environment-health, failure-search, versioning, and catalog experiences that make training data easy to understand, manage, and extend.
• Establish a shared component kit and use it to build self-serve interfaces for creating and improving tasks with quality checks inline.

Requirements

• You've shipped full-stack products and owned systems from user interface through storage or services.
• You've built dense, data-facing tools such as transcript viewers, diffing systems, review queues, observability products, or operational dashboards.
• You've built or maintained a design system or component library.
• You've designed review, QA, moderation, fraud, or acceptance workflows.
• You care about data quality and are willing to inspect raw data.