About this role
About the Role
Build product interfaces, backend systems, and internal tools for a reinforcement learning data platform. You will own end-to-end experiences that help research teams and external partners create, evaluate, and improve training data.
What You'll Do
-
Develop tools for browsing environments, inspecting trajectories, reviewing task quality, and understanding model behavior.
-
Build partner workflows for creating, submitting, testing, and iterating on reinforcement learning environments and training data.
-
Create dashboards and observability tools for environment quality, evaluation results, data collection progress, and pipeline health.
-
Design backend services and APIs that connect task authoring, data collection, evaluation, quality assurance, and training infrastructure.
-
Work with research, operations, and go-to-market teams to ship useful systems quickly, even when requirements are evolving.
What We're Looking For
-
At least 3 years of full-stack engineering experience building and shipping production systems.
-
Strong Python skills and experience with React, TypeScript, Next.js, or a comparable modern web stack.
-
Experience owning user-facing or internal products end-to-end, from design through deployment.
-
Hands-on experience with cloud infrastructure, Docker, CI/CD, and production debugging.
-
Experience building dashboards, monitoring or debugging tools, data collection or evaluation platforms, and partner-facing workflows.
-
Knowledge of backend services, APIs, and databases that connect multiple system components.
-
Strong product judgment and communication skills, with the ability to build intuitive tools for technical and non-technical users.
-
A technical background or shipped work that demonstrates mid-to-senior engineering depth.
Compensation & Benefits
Base salary is $130,000 to $225,000 annually. Visa sponsorship and relocation support are available for full-time candidates relocating to the United States or Singapore.
Location
On-site in San Francisco or Singapore, with remote candidates considered if they can maintain 70% to 80% time zone overlap with either location.