RL Inference Engineer - Large-Scale AI & LLMs

Maven Ventures; Palo Alto (CA); On-site; USD 180,000 - 440,000; Full time

Job summary

SpaceXSI is building Super Intelligence to help humanity understand the universe. The RL infrastructure team seeks an engineer to design and optimize the inference stack for RL workloads, from ablations to production training runs.

Required experience includes Python, C++ and/or Rust, and frameworks such as PyTorch, Jax, CUDA. You will analyze bottlenecks, collaborate with the modeling team on efficient RL techniques, and develop scalable inference engines.

Qualifications

• Experience with Python, C++ and/or Rust, and frameworks such as PyTorch, Jax, CUDA

Responsibilities

• Design and optimize our inference stack for all shapes of RL workloads at SpaceXSI, from small scale ablations to production training runs
• Analyze, profile and address performance bottlenecks in large scale RL systems
• Work closely with the modeling team to efficiently implement novel RL techniques and algorithms

Skills

Python

C++/Rust

PyTorch

Jax

CUDA

Tools

SGLang

vLLM

Job description

SpaceXSI is building Super Intelligence to help humanity understand the universe. The RL infrastructure team seeks an engineer to design and optimize the inference stack for RL workloads, from ablations to production training runs.

Required experience includes Python, C++ and/or Rust, and frameworks such as PyTorch, Jax, CUDA. You will analyze bottlenecks, collaborate with the modeling team on efficient RL techniques, and develop scalable inference engines.