Member of Technical Staff - RL Training Framework

at SpaceXAI

📍 Palo Alto, United States

USD 180,000-440,000 per year

MIDDLE

✅ On-site

Tech Stack
Tag name is followed by "@" symbol and proficiency level value. About proficiency levels:

1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;

3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;

7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;

10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.

AI Debugging @ 3 Distributed Systems @ 3 JAX @ 5 LLM @ 3 Observability Python @ 5 Reinforcement Learning @ 6 Rust @ 5

Details

The RL infrastructure team is looking for an engineer to help develop the reinforcement learning training framework. The team develops AI systems and operates with a hands-on, engineering-focused culture.

Responsibilities

Design and implement the systems supporting all reinforcement learning workloads, from small-scale ablations to production training runs.
Profile, debug, and optimize end-to-end training performance.
Improve the scalability and observability of the reinforcement learning stack.

Requirements

Experience building, debugging, and optimizing the efficiency of large-scale distributed systems.
Ability to work in unfamiliar areas and solve problems at all levels of the stack.
Proficiency in one or more of Python, JAX, Rust, and C++.
Experience with large-scale LLM training infrastructure is preferred.
Strong knowledge of reinforcement learning techniques is preferred.
Experience with reinforcement learning numerics is preferred.