GPU Kernel Engineer — Fast ML Training

MakerMaker.AI; San Francisco (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

MakerMaker.AI in San Francisco is seeking a skilled Software Engineer to write and optimize GPU kernels. You will work on deep low-level tasks that directly impact the performance of machine learning models.

The ideal candidate has over 4 years of experience with GPU kernels, strong systems expertise, and a proven track record in kernel optimizations. This role requires on-site work in a collaborative environment.

Qualifications

• 4+ years writing performant GPU kernels (CUDA, ROCm, Triton, or equivalent).
• Fluency with memory hierarchy, occupancy, and tensor cores.
• Previous experience shipping kernel-level optimizations.

Responsibilities

• Write and optimize GPU kernels for training and inference workloads.
• Profile workloads and translate findings into kernel optimizations.
• Integrate optimized kernels into training and serving stacks.

Skills

Performance optimization

CUDA

Profiling tools

Systems expertise

Python

C++

Tools

Nsight

ncu

Job description

MakerMaker.AI in San Francisco is seeking a skilled Software Engineer to write and optimize GPU kernels. You will work on deep low-level tasks that directly impact the performance of machine learning models.

The ideal candidate has over 4 years of experience with GPU kernels, strong systems expertise, and a proven track record in kernel optimizations. This role requires on-site work in a collaborative environment.