M
About the role
Optimize Mistral's open-weight model serving stack. Squeeze latency and throughput out of cutting-edge GPUs.
Requirements
CUDA / Triton experience. Familiarity with vLLM, TensorRT-LLM, or SGLang.
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.