Staff Engineer, RL Inference & Efficiency

Maxxd; Palo Alto (CA); Hybrid; USD 180,000 - 440,000; Full time

Benefits offered by this job

Equity

Medical, vision, dental

401(k) retirement plan

Job summary

SpaceXSI is seeking a Member of Technical Staff - RL Inference to design and optimize the RL inference stack for diverse workloads, from ablations to production runs. The role emphasizes performance profiling, and collaboration with the modeling team to implement advanced RL methods.

Candidates should be expert in distributed systems and LLM inference, with proficiency in Python, C++, or Rust, and frameworks like PyTorch, Jax, and CUDA. SpaceXSI offers a comprehensive rewards package and equity.

Qualifications

• Experience in building, debugging, and optimizing large-scale distributed systems.
• Experience in LLM inference.
• Proficiency in 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.

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

PyTorch

Jax

CUDA

Tools

SGLang

vLLM

Job description

SpaceXSI is seeking a Member of Technical Staff - RL Inference to design and optimize the RL inference stack for diverse workloads, from ablations to production runs. The role emphasizes performance profiling, and collaboration with the modeling team to implement advanced RL methods.

Candidates should be expert in distributed systems and LLM inference, with proficiency in Python, C++, or Rust, and frameworks like PyTorch, Jax, and CUDA. SpaceXSI offers a comprehensive rewards package and equity.