R
Model Performance Engineer (Remote — Worldwide)
CUDATritonInferencevLLM
About the role
Make open-source models run blazingly fast on Replicate. Fully remote.
Responsibilities
Optimize hot models, build serving infra, reduce cost per token.
Requirements
CUDA, Triton, kernel optimization, inference engines.
Benefits
Equity, benefits, remote.
Disclaimer: MMagic.ai connects talented people with AI companies around the world. While we work hard to feature quality opportunities, we don't independently verify employers, candidates, salaries, or hiring outcomes. We encourage you to research each opportunity and company before applying or making an offer.