Full-Stack RL Research Tools Engineer

Cursor; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Cursor is seeking a Software Engineer on the RL Data team to design and build tools used by researchers and external contributors for creating, reviewing, submitting, and monitoring reinforcement-learning environments and tasks.

You will own the end-to-end review and acceptance experience, from rollout and transcript inspection to task-quality signals analysis, and you will build authoring interfaces for researchers, vendors, and domain experts to create and improve environments quickly and

Qualifications

• Shipped full-stack products with UI through storage or services.
• Experience with data-facing tools and structured data rendering.
• Experience building or maintaining a design system or component library is a plus.
• Designed review, QA, moderation, or acceptance workflows to ensure data integrity.
• Familiarity with evaluations, graders, reinforcement learning, or data-quality systems helpful.
• Ability to move quickly under ambiguity and work with researchers and domain experts.

Responsibilities

• Create fast, trustworthy workflows for vendors and research team to interact with each other.
• Build review tools for inspecting and comparing rollouts, transcripts, and grader outputs.
• Develop environment-health, failure-search, versioning, and catalog experiences for training data.
• Establish a shared component kit and self-serve interfaces for creating and improving tasks with quality checks.

Skills

TypeScript

React

Node.js

Python

Go

Job description

Cursor is seeking a Software Engineer on the RL Data team to design and build tools used by researchers and external contributors for creating, reviewing, submitting, and monitoring reinforcement-learning environments and tasks.

You will own the end-to-end review and acceptance experience, from rollout and transcript inspection to task-quality signals analysis, and you will build authoring interfaces for researchers, vendors, and domain experts to create and improve environments quickly and