> Markdown version of [/jobs/ext/4344358-rl-environment-software-engineer](https://www.wearedevelopers.com/jobs/ext/4344358-rl-environment-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# RL Environment Software Engineer

- **Company:** ONE STOP COLLECTIBLE CORP
- **Location:** San Francisco, CA, United States
- **Salary:** $180,000.0 - $220,000.0
- **Contract:** Permanent contract
- **Skills:** Python (Programming Language), Machine Learning, Node.Js, TypeScript, Reinforcement Learning, ReactJS, Backend, Build Management, Kubernetes, Information Technology, Build Tools, Front End Software Development, Docker
- **Published:** October 12, 2026
- **Apply:** https://startup.jobs/rl-environment-software-engineer-afterquery-talentpluto-10409716

## About the Role

* Strong machine-learning engineers who code heavily and build systems from scratch, with strong intuition for reinforcement learning.
 * Proficiency across a modern stack, Node.js and Python on the backend and React/TypeScript on the frontend, with strong Kubernetes and Docker skills.
 * Comfort operating in a fast-paced startup environment with high ownership and long hours.
 * A track record of meaningful tenure and impact at previous companies.
 * Reinforcement-learning experience or an RL research background is a strong plus, though not required.
 * Bachelor's degree in computer science or a related technical field, or equivalent practical experience.

## Description

* Design and build high-quality RL environments that simulate real working environments end to end.
 * Develop agents for the tasks within those environments and iterate until they are efficient and production-ready.
 * Partner with the research team to scope which environments to build and why, staying ahead of future demand rather than only meeting present needs.
 * Own the backend and infrastructure layers that make environments reliable and scalable.
 * Help set engineering standards for a zero-to-one team as the RL function grows.