Staff RL Inference Engineer - Large-Scale Systems

SpaceXAI

Palo Alto (CA)

On-site

USD 180,000 - 440,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

SpaceXAI, based in Palo Alto, is seeking an engineer to help advance low precision RL training and inference within the RL infrastructure team. You will design and optimize the inference stack for diverse RL workloads, from ablations to production training runs, and work with the modelling team to implement novel RL techniques.

The role requires building and debugging high-performance, distributed systems, with a focus on LLM inference, and strong coding in Python, C++, or Rust, leveraging

Qualifications

  • 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.

Responsibilities

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

SpaceXAI, based in Palo Alto, is seeking an engineer to help advance low precision RL training and inference within the RL infrastructure team. You will design and optimize the inference stack for diverse RL workloads, from ablations to production training runs, and work with the modelling team to implement novel RL techniques.

The role requires building and debugging high-performance, distributed systems, with a focus on LLM inference, and strong coding in Python, C++, or Rust, leveraging

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

RL Inference Engineer: Low-Precision ML at Scale
RL Inference Engineer: Low-Precision ML at Scale

SpaceX Super Intelligence • Palo Alto (CA)

On-site
USD 180,000 - 440,000
Equity
Health insurance
401(k) retirement plan
+2
Senior RL Inference Engineer — Large-Scale ML, Equity
Senior RL Inference Engineer — Large-Scale ML, Equity

Maven Ventures • Palo Alto (CA)

On-site
USD 180,000 - 440,000
Equity
Medical coverage
Vision coverage
+4
RL Training Infrastructure Engineer
RL Training Infrastructure Engineer

SpaceX Super Intelligence • Palo Alto (CA)

On-site
USD 180,000 - 440,000
Equity
Medical insurance
Dental coverage
+5
Member of Technical Staff - RL Inference
Member of Technical Staff - RL Inference

SpaceXAI • Palo Alto (CA)

On-site
USD 180,000 - 440,000
Senior RL Training Engineer – Scalable AI Stack
Senior RL Training Engineer – Scalable AI Stack

SpaceXAI • Palo Alto (CA)

On-site
USD 180,000 - 400,000
Equity
Medical coverage
Vision coverage
+5
Senior RL Training Framework Engineer
Senior RL Training Framework Engineer

X AI • Palo Alto (CA)

On-site
USD 180,000 - 400,000
Equity
Medical, vision, dental
401(k) retirement plan
+2
Sr. Model Engineer, RL Inference
Sr. Model Engineer, RL Inference

X.ai • Palo Alto (CA)

On-site
USD 180,000 - 440,000
Equity
Medical coverage
Vision coverage
+4
Sr. Model Engineer, RL Inference
Sr. Model Engineer, RL Inference

SpaceX Super Intelligence • Palo Alto (CA)

On-site
USD 180,000 - 440,000
Equity
Health insurance
401(k) retirement plan
+2
Senior RL Training Systems Engineer
Senior RL Training Systems Engineer

SpaceXSI • Palo Alto (CA)

On-site
USD 180,000 - 400,000
Equity
Medical
Vision
+5
Senior RL Model Engineer - Scalable Training Framework
Senior RL Model Engineer - Scalable Training Framework

SpaceX Super Intelligence • Palo Alto (CA)

On-site
USD 180,000 - 400,000
Equity
Medical, Vision, Dental
401(k) retirement plan
+2