Senior Accelerated Computing Architect — Equity Options

NVIDIA Corporation; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a Senior Accelerated Computing Architect to advance performance on our GPUs and drive co-design of software and hardware across HPC, AI, and automotive workloads. You will collaborate with hardware, software, product, and research teams to optimize core algorithms and reference codes.

Join a world-class team and help push architectures to their limits. The role emphasizes CUDA/OpenCL, C/C++, and multi-node performance benchmarking, with opportunities for impact and innovation.

Qualifications

• MS or PhD in CS/CE/EE or equivalent with 6+ years of experience.
• Strong mathematical fundamentals (linear algebra, numerical methods).
• Hands-on CUDA or OpenCL experience.
• Familiarity with MPI/OpenSHMEM/NVSHMEM is a plus.
• Strong C/C++ knowledge with good software design and algorithms.
• Good communication and organizational skills.
• Experience benchmarking and profiling workloads on GPU/CPU clusters.

Responsibilities

• Analyze and optimize performance on current/next-generation NVIDIA GPUs.
• Create and optimize core parallel algorithms, data structures, and reference codes.
• Understand hardware-software interplay on core algorithms, programming models, and applications.
• Collaborate with hardware, software, product, and research teams to guide direction.
• Dive into accelerated computing applications for software-hardware co-design.
• Document results via papers, conference publications, blogs, or patents as appropriate.

Skills

GPU programming (CUDA/OpenCL)

C/C++ programming

Python programming

Performance optimization

Communication & collaboration

Education

MS or PhD in CS/CE/EE or equivalent

Tools

MPI

OpenSHMEM/NVSHMEM

Unix IPC

Threading APIs

Job description

NVIDIA is seeking a Senior Accelerated Computing Architect to advance performance on our GPUs and drive co-design of software and hardware across HPC, AI, and automotive workloads. You will collaborate with hardware, software, product, and research teams to optimize core algorithms and reference codes.

Join a world-class team and help push architectures to their limits. The role emphasizes CUDA/OpenCL, C/C++, and multi-node performance benchmarking, with opportunities for impact and innovation.