G
Inference Software Engineer (Remote — Worldwide)
FeaturedC++CUDALLMsCompilersPerformance
About the role
Squeeze every microsecond out of LPU inference for production LLM workloads. Remote, worldwide.
Responsibilities
Optimize attention/MoE kernels and serving runtime.
Requirements
C++/CUDA, kernel optimization, transformer internals.
Benefits
Equity, premium health, learning budget.
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.