AI Computing Software Development Engineer, LLM Inference — Nvidia | cvGO!

Nvidia · 2 Locations · Office

### About the Role Develop high-performance software for LLM inference on NVIDIA GPUs. Work at the intersection of systems programming and ML to accelerate modern AI applications. ### Responsibilities - Develop and optimize LLM inference libraries (e.g., TensorRT-LLM) - Profile and improve CUDA kern