Get more replies from employers
Send a job-specific resume in minutes.
NVIDIA AI in Santa Clara, CA seeks an architect to design and implement features for the CUDA Driver, optimizing GPU kernel scheduling and AI/ML workloads. You will drive enhancements across the compute stack and coordinate with cross-team partners to advance CUDA programming models.
The role demands strong C/C++, system-level software experience, and a proven ability to work on low-latency Linux kernel/OS interfaces in a multi-threaded environment.
Architect and implement new features for the CUDA Driver to optimize GPU kernel scheduling and AI/ML workloads. Collaborate across teams to extend CUDA programming models and improve the overall compute platform.
Requires a degree in Computer Science or Electrical Engineering with at least 4 years of experience in C/C++ and system-level software development. Candidates should have a strong understanding of OS interfaces, memory management, and multithreaded programming.
C, C++, CUDA, Device Drivers, Multithreading, Operating Systems, System Architecture, Kernel Mode Development, Parallel Computing, Linux Systems Software, Virtual Memory, Memory Hierarchy