NVIDIA Corporation in Santa Clara, CA is seeking outstanding AI systems engineers to develop groundbreaking inference technologies for the hardware-accelerated stack. You will create libraries, code generators, and GPU kernel innovations for LLM workloads.
Join a team that designs extensible abstractions for LLM serving engines, builds just-in-time compilers, and collaborates with DL frameworks and GPU architecture groups. Experience with PyTorch/TensorFlow and CUDA is essential.
#J-18808-Ljbffr