> Markdown version of [/jobs/ext/4196998-software-engineer-rl-training-framework](https://www.wearedevelopers.com/jobs/ext/4196998-software-engineer-rl-training-framework). 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).

---

# Software Engineer, RL Training Framework

- **Company:** Space X
- **Location:** Palo Alto, CA, United States
- **Salary:** $180,000.0
- **Contract:** Permanent contract
- **Skills:** C++ (Programming Language), Software Debugging, Distributed Systems, Python (Programming Language), Reinforcement Learning, Large Language Models
- **Published:** October 13, 2026
- **Apply:** https://www.thejobnetwork.com/job/efa39acc-8fef-4dca-a1ad-30fd674e332b/software-engineer-rl-training-framework

## About the Role

* Experience building, debugging, and optimizing efficiency of large-scale distributed systems
 * Proficiency in Python, Jax, Rust, and/or C++

PREFERRED SKILLS AND EXPERIENCE:

 * Experience with large scale LLM training infrastructure
 * Strong knowledge of reinforcement learning techniques
 * Experience with RL numerics
 * Comfortable diving into unfamiliar areas and solving problems at all levels of the stack

## Description

* Design and implement the systems backing all RL workloads at SpaceXSI, from small scale ablations to production training runs
 * Profile, debug, and optimize end-to-end training performance
 * Improve scalability and observability of the RL stack