Full-Stack Software Engineer, Reinforcement Learning (Mid-Level)
About the Role
Build product interfaces, backend services, and internal tools for an AI infrastructure platform focused on reinforcement learning data and evaluation. You will work closely with research, operations, and external partners to turn complex needs into useful, reliable products.
What You'll Do
Develop interfaces for browsing environments, inspecting model trajectories, reviewing task quality, and understanding model behavior.
Build workflows that help external partners create, submit, test, and improve 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 review, and training systems.
Collaborate with research, operations, and go-to-market teams to ship and improve products in a fast-moving environment.
What We're Looking For
At least 3 years of experience building and shipping production full-stack software.
Proficiency in Python and a modern web stac
