Member of Technical Staff - RL Inference

xAI • Palo Alto, CA

2d

About The Position

The RL infrastructure team is looking for an engineer to help with low precision RL training and inference. The role involves designing and optimizing the inference stack for various RL workloads, analyzing and addressing performance bottlenecks in large-scale RL systems, and collaborating with the modeling team to implement novel RL techniques and algorithms.

Requirements

• Experience in building, debugging, and optimizing efficiency of large-scale distributed systems
• Experience in LLM inference
• Proficiency in programming languages such as Python, C++ and/or Rust; frameworks such as PyTorch, Jax, CUDA
• Willingness to dive deep and solve hardcore problems at all levels of the stack

Nice To Haves

• Strong knowledge in quantization and numerics in LLM inference and training
• Experience in developing inference engines, e.g. SGLang, vLLM

Responsibilities

• Design and optimize our inference stack for all shapes of RL workloads at xAI, 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

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed