Software Engineer, ML Research Tools

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

Our mission is to automate coding. The first step in our journey is to build the best tool for professional programmers, using a combination of inventive research, design, and engineering. Our organization is very flat, and our team is small and talent dense. We particularly like people who are truth-seeking, passionate, and creative. We enjoy spirited debate, crazy ideas, and shipping code.

About the role

As a Software Engineer on the RL Data team, you’ll design and build the tools that researchers and external contributors use to create, review, submit, and monitor the 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, task‑quality signals grader and reward‑hacking analysis, to the workflows that move a submission into training. From there, you’ll build authoring interfaces that let researchers, vendors, and domain experts create and improve environments and tasks quickly and confidently.

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

What you’ll work on

• Create fast, trustworthy workflows for vendors and research team to interact effectively with each other — vendor task creation and iteration, vendor submissions, and task acceptance into training.

• 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, then use it to build self-serve interfaces for creating and improving tasks with quality checks inline.

You may be a fit if

• You’ve shipped full-stack products and owned systems from user interface through storage or services, using technologies such as TypeScript and React alongside Node, Python, or Go.

• You’ve built dense, data-facing tools such as transcript viewers, diffing systems, review queues, observability products, or operational dashboards—and you have strong opinions about how structured data should be rendered.

• You’ve built or maintained a design system or component library and can establish durable product and engineering conventions for a fast-moving team.

• You’ve designed review, QA, moderation, fraud, or acceptance workflows where users had an incentive to get past the checks, and you know how to keep those systems honest.

• You care about data quality, and are willing to inspect raw data. Experience with evaluations, graders, reinforcement learning, or data-quality systems is helpful but not required.

• You move quickly under ambiguity, collaborate closely with researchers and domain experts, and take open-ended problems from rough need to reliable product.