About the Role
You will design and build full-stack tools for creating, reviewing, submitting, monitoring, and accepting reinforcement-learning environments and tasks. You will own review and acceptance workflows, build authoring interfaces, and develop data-management experiences that make training data easy to understand and improve.
Requirements
- Experience shipping full-stack products from user interface through storage or services
- Experience with TypeScript and React alongside Node, Python, or Go
- Experience building dense data-facing tools such as transcript viewers, diffing systems, review queues, observability products, or operational dashboards
- Experience building or maintaining a design system or component library
- Experience designing review, QA, moderation, fraud, or acceptance workflows
- Knowledge of data quality and willingness to inspect raw data
- Ability to collaborate with researchers and domain experts and take open-ended problems to reliable products
Responsibilities
- Create workflows for vendor task creation, iteration, submission, and acceptance into training
- Build review tools for rollouts, transcripts, grader outputs, and task-quality signals
- Develop environment-health, failure-search, versioning, and catalog experiences
- Establish a shared component kit
- Build self-service interfaces for creating and improving tasks with inline quality checks
Hiring Process
Two or three short technical interviews focused on frontend craft for dense data and system design, followed by an onsite small project using real rollouts, idea discussions, and team meetings.