Remote job
Full-Stack Software Engineer, Reinforcement Learning
Job details
About this role
Role overview Build product interfaces, backend services, and internal tools for a reinforcement learning data platform. The systems will help research teams and external partners create and assess training data, while providing visibility into evaluation, data collection, and platform health.
Responsibilities - Develop tools for exploring environments, inspecting trajectories, reviewing task quality, and understanding model behavior. - Build partner workflows for creating, submitting, testing, and refining environments and training data. - Create dashboards and observability tools for environment quality, evaluation results, collection progress, and pipeline health. - Design backend services and APIs that connect authoring, collection, evaluation, quality review, and reinforcement learning infrastructure. - Work with research, operations, and go-to-market teams to ship useful systems as requirements evolve.
Requirements - At least three years of full-stack engineering experience building and shipping production systems. - Strong Python skills and experience with a modern web stack such as React, TypeScript, or Next.js. - Experience owning user-facing or internal products from design through deployment. - Hands-on experience with cloud infrastructure, Docker, CI/CD, and production debugging. - Experience with dashboards, monitoring, observability, or debugging tools for complex systems. - Experience with data collection, labeling, annotation, or evaluation platforms, and with APIs and databases that connect system components. - Strong product judgment and communication across technical and non-technical teams; a technical degree or a portfolio showing technical depth is expected.
Nice to have - Experience building workflows for external partners.
Benefits and work setup - Annual base salary of $130,000–$225,000. - Visa sponsorship and relocation support are available for qualifying full-time candidates moving to the United States or Singapore. - On-site or remote. Remote candidates should be able to maintain 70%–80% time-zone overlap with San Francisco or Singapore.