RL Environment Software Engineer

Location: San Francisco, California, United States; Work model: On-site

Base compensation: $180K–$220K; approximate OTE of $400K+ through uncapped profit share

Company

Applied AI research lab building reinforcement-learning environments and agents for leading AI labs, with a focus on quality and rapid expansion into new domains.

What you will do

• Design and build reinforcement-learning environments that simulate real working environments end to end.
• Develop, test, and optimize agents for tasks within those environments until they are production-ready.
• Partner with researchers to identify future environment needs and define which systems to build.
• Own backend and infrastructure layers that make environments reliable and scalable.
• Help establish engineering standards for a new RL team as it grows into industry-focused pods.

Requirements

• Strong machine-learning engineering experience with substantial coding and the ability to build systems from scratch.
• Strong intuition for reinforcement learning and experience operating at the intersection of research and software engineering.
• Proficiency with Node.js and Python on the backend, React and TypeScript on the frontend, plus Kubernetes and Docker.
• Ability to work in a fast-paced startup environment with high ownership and long hours.
• Meaningful tenure and demonstrated impact at previous companies.
• Bachelor’s degree in computer science or a related technical field, or equivalent practical experience.

Nice to have

• Reinforcement-learning experience or an RL research background.

Culture & Benefits

• High-ownership environment with a focus on building systems from the ground up.
• Opportunity to join a newly formed RL team and grow with the function.
• Uncapped profit share contributing to approximately $400K+ OTE.
• Work is performed on-site in San Francisco.