Full-Stack Software Engineer, Reinforcement Learning
About the role
About HUD
HUD is building infrastructure to create RL training data and evals for frontier AI agents, as well as a marketplace to sell these to frontier labs through the HUD marketplace. Our platform is used by frontier labs, Fortune 500 companies, and startups. We’ve raised $16M from top VCs and were YC W25.
About the role
We’re looking for a Full-Stack Software Engineer, Reinforcement Learning to build the product surfaces, backend systems, and internal tools that power HUD’s RL data engine.
You’ll own product surfaces end-to-end, including backend services, APIs, databases, dashboards, tools, vendor workflows, data collection, and observability for RL rollouts. You don’t need to be a researcher, but you need to work research engineers and vendors to translate ambiguous needs into polished products that enable our RL systems.
Responsibilities
-
Develop product-facing tools for browsing environments, inspecting trajectories, reviewing task quality, debugging failures, and understanding model behavior
-
Build vendor-facing workflows that make it easy for external partners to create, submit, test, and iterate on RL environments and training data
-
Create dashboards and observability tools that surface environment quality, eval results, data collection progress, grader issues, reward signal problems, and pipeline health
-
Design backend services and APIs that connect task authoring, data collection, evaluation, QA/QC, and RL training infrastructure
-
Partner closely with research, operations, and GTM teams to turn vague, high-stakes requests into well-designed systems that ship quickly
Experience
You may be a good fit if you have:
