RL Inference Engineer - Scalable ML Inference

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

Job summary

SpaceXSI in Palo Alto is seeking a Member of Technical Staff for RL inference. You will help design and optimize our RL inference stack and support low precision training and inference across workloads, from experiments to production runs.

You will profile and address performance bottlenecks in large-scale RL systems, and collaborate with the modelling team to implement novel RL techniques and algorithms using Python, C++, Rust and relevant ML frameworks.

Qualifications

• Experience in building, debugging, and optimizing efficiency of large-scale distributed systems.
• Experience in LLM inference.
• Proficiency in Python, C++ and/or Rust; 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 modelling team to efficiently implement novel RL techniques and algorithms

Skills

Distributed systems

LLM inference

Python

C++

Rust

Performance profiling

Optimization

PyTorch

JAX

CUDA

Tools

PyTorch

JAX

CUDA

SGLang

vLLM

Job description

SpaceXSI in Palo Alto is seeking a Member of Technical Staff for RL inference. You will help design and optimize our RL inference stack and support low precision training and inference across workloads, from experiments to production runs.

You will profile and address performance bottlenecks in large-scale RL systems, and collaborate with the modelling team to implement novel RL techniques and algorithms using Python, C++, Rust and relevant ML frameworks.