Senior Deep Learning Software Engineer, Inference

A Senior Software Engineer focused on Deep Learning Inference responsible for designing, building, and optimizing GPU-accelerated software that powers advanced AI applications. The role centers on developing and improving inference frameworks (such as SGLang and vLLM) and enabling efficient deployment of large-scale language and generative models across NVIDIA accelerators. The position collaborates with the deep learning community and internal teams to deliver high-performance model serving solutions.