Senior CUDA Kernel Engineer - Tensor Core GEMM

NVIDIA; Hillsboro (OR); On-site; USD 152,000 - 241,500; Full time

Benefits offered by this job

Equity

Comprehensive benefits

Job summary

NVIDIA is looking for talented individuals to join their CUTLASS team in Hillsboro, Oregon. This role focuses on developing and optimizing deep learning kernels using Tensor Core technology, enhancing performance on NVIDIA GPUs.

The ideal candidate will possess a Masters or PhD in related fields and strong experience in C++. NVIDIA offers a competitive salary ranging from $152,000 to $241,500 for Level 3 and $184,000 to $287,500 for Level 4, along with equity and benefits.

Qualifications

• 3+ years of relevant industry experience.
• Deep understanding of computer architecture.
• Experience working at the assembly level.

Responsibilities

• Develop Tensor Core-based deep learning kernels using CUTLASS.
• Optimize kernels for peak throughput on silicon and software simulators.
• Collaborate with teams for fast kernel delivery.

Skills

C++ programming

CUDA

Software design

Debugging

Performance evaluation

Education

Masters or PhD in Computer Science or Engineering

Tools

OpenCL

HIP

SYCL

Mojo

Pallas

Triton

Mosaic

Halide

Job description

NVIDIA is looking for talented individuals to join their CUTLASS team in Hillsboro, Oregon. This role focuses on developing and optimizing deep learning kernels using Tensor Core technology, enhancing performance on NVIDIA GPUs.

The ideal candidate will possess a Masters or PhD in related fields and strong experience in C++. NVIDIA offers a competitive salary ranging from $152,000 to $241,500 for Level 3 and $184,000 to $287,500 for Level 4, along with equity and benefits.