CUDA System Software Engineer - Performance & GPU Kernel

NVIDIA AI in Santa Clara seeks a systems software engineer to design and implement performance-centric features for the CUDA driver and runtime using C/C++. You will analyze critical paths across software and hardware to boost latency, throughput, and scalability. The role requires a CS degree and at least two years in systems software, with strong C/C++, OS, and architecture skills. Collaboration across teams to optimize GPU drivers and kernel code is essential.