Principal Architect, Accelerated Computing
Core
Designing software and system architectures for accelerated high performance computing, scientific computing, machine learning, AI, datacenter, and automotive computing on NVIDIA GPUs.
Role type
Principal Architect, Accelerated Computing
Builds
High performance computing solutions for datacenter and automotive applications
Domain
Hardware-software co-design for accelerated computing (GPUs)
Deliverable
production ML models
Required skills
Parallel algorithm design, GPU programming (CUDA/OpenCL), C/C++, performance optimization, hardware-software architecture analysis, benchmarking and profiling
Preferred skills
Multi-node communication APIs (MPI, OpenSHMEM/NVSHMEM), threading APIs, Python, Unix-style IPC
Technologies
CUDA, OpenCL, MPI, OpenSHMEM, NVSHMEM, C, C++, Python
Responsibilities
Optimize core parallel algorithms and data structures for NVIDIA GPUs, collaborate with hardware design and software engineering teams, lead software-hardware co-design initiatives, publish white papers and conference publications
Seniority
Principal, hands-on IC with strategic leadership
