Develop product-facing tools for browsing environments, inspecting trajectories, reviewing task quality, debugging failures, and understanding model behavior.
Build vendor-facing workflows for creating, submitting, testing, and iterating on RL environments and training data.
Create dashboards and observability tools for environment quality, evaluation results, data collection progress, grader issues, reward signals, and pipeline health.
Design backend services and APIs connecting task authoring, data collection, evaluation, QA/QC, and RL training infrastructure.
Partner with research, operations, vendors, GTM teams, engineering, and founders to turn ambiguous requests into well-designed systems.
Requirements
Strong software engineering fundamentals and full-stack range, including Python and a modern web stack such as React, TypeScript, Next.js, or similar.
Experience owning user-facing or internal products end-to-end.
Ability to build intuitive tools for technical and non-technical users.
Comfort with cloud infrastructure, Docker, CI/CD, observability, and production debugging.
Strong communication skills and high agency in identifying, building, and improving systems.
Preferred experience with data collection, labeling, annotation, evaluation, research tooling, dashboards, review workflows, observability tools, debugging interfaces, developer tools, infrastructure products, internal platforms, or workflow products.
Experience with AWS, Kubernetes, Terraform, Docker, Grafana, or similar infrastructure tools is preferred.
The company prioritizes technical aptitude and learning potential over years of experience.
Benefits
Full-time, on-site work in the San Francisco Bay Area or Singapore offices.
Relocation and visa support for strong full-time candidates joining the US or Singapore offices.
100% covered medical, dental, and vision insurance from Blue Shield of CA for US employees.
Lunch and dinner provided in the office.
Company-wide holiday break from Christmas Eve through New Year’s Day, in addition to PTO and paid holidays.
Equinox membership, 401k, and commuter benefits for US employees.
Unlimited access to tokens for ChatGPT, Claude Code, Cursor, and similar tools.
Applications are rolling and the process includes two technical interviews and a 2–3 day work trial.
HUD
The platform to build RL environments. We help improve frontier models across diverse capabilities and help build post-training datasets for doing RFT.