Senior RL Inference Engineer — Large-Scale ML, Equity

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

Benefits offered by this job

Equity

Medical coverage

Vision coverage

Dental coverage

401(k) retirement plan

Disability insurance

Life insurance

Job summary

SpaceXSI is seeking a Senior Model Engineer focused on RL inference to advance our RL infrastructure. You will design scalable inference stacks, profile performance bottlenecks, and work with the modeling team to implement cutting-edge RL techniques for large models.

The role emphasizes production-quality Python/C++/Rust code and experience with large-scale distributed RL workloads. Join us to push the frontier of AI at SpaceXSI.

Qualifications

• Experience writing production-quality code in Python, PyTorch, JAX, Rust, or C++.
• Experience training large models (1B+ parameters).
• Experience in building and optimizing RL inference systems.

Responsibilities

• Design and optimize the inference stack for RL workloads.
• Profile and address performance bottlenecks in large-scale RL systems.
• Collaborate with modeling team to implement RL techniques and algorithms.

Skills

Python

PyTorch

JAX

Rust

C++

Tools

SGLang

vLLM

Job description

SpaceXSI is seeking a Senior Model Engineer focused on RL inference to advance our RL infrastructure. You will design scalable inference stacks, profile performance bottlenecks, and work with the modeling team to implement cutting-edge RL techniques for large models.

The role emphasizes production-quality Python/C++/Rust code and experience with large-scale distributed RL workloads. Join us to push the frontier of AI at SpaceXSI.