GPU Kernel Engineer — High-Performance ML at Scale

The Consensus; San Francisco (CA); On-site; USD 120,000 - 160,000; Full time

Benefits offered by this job

Competitive compensation with equity

100% medical, dental, and vision insurance coverage

Flexible PTO policy including a Winter Break

Paid parental leave

Fertility and family-building stipend

Job summary

The Consensus is looking for a GPU Kernel Engineer to optimize machine learning performance. The ideal candidate will design high-performance GPU kernels and collaborate on cutting-edge projects in the AI field. This role offers substantial growth opportunities in an inclusive environment.

You'll be a critical part of shaping AI applications, working with state-of-the-art tools, and contributing to significant advancements in GPU performance.

Qualifications

• Proficient in optimizing code using CUDA and PTX assembly.
• Knowledge of memory access patterns and bandwidth optimization.
• Experience with GPU kernel libraries such as Cutlass and Triton.

Responsibilities

• Design and implement high-performance GPU kernels for ML operations.
• Collaborate with research teams to productionize advancements.
• Contribute to internal and open-source GPU libraries.

Skills

Strong understanding of GPU architecture

Proficient in C++

Experience with GPU performance profiling tools

Tools

CUDA C++ API

Nsight Systems

Torch Profiler

Job description

The Consensus is looking for a GPU Kernel Engineer to optimize machine learning performance. The ideal candidate will design high-performance GPU kernels and collaborate on cutting-edge projects in the AI field. This role offers substantial growth opportunities in an inclusive environment.

You'll be a critical part of shaping AI applications, working with state-of-the-art tools, and contributing to significant advancements in GPU performance.