TensorRT Performance Engineer

NVIDIA in Santa Clara is seeking an experienced Deep Learning Software Engineer focused on TensorRT performance to analyze and optimize the inference stack across datacenter GPUs and edge accelerators. You will work on graph compilers, quantization and distributed inference to set the standard for Gen AI performance. Join a team pushing high‑performance inference software with strong C++/Python skills, collaborating across NVIDIA accelerators and OSS projects to deliver cutting‑edge DL solutions. #J-18808-Ljbffr