CUDA Kernel Optimization Specialist

Stack

Responsibilities

• ▹Analyze and optimize GPU kernels for performance, efficiency, and hardware utilization
• ▹Use profiler metrics such as L2 cache hit rate, L2 throughput, and occupancy to guide kernel improvements
• ▹Review GPU kernel implementations to identify bottlenecks without needing extensive algorithmic background
• ▹Write, modify, and reason about C++17, Python, and GPU programming code
• ▹Apply CUDA, HIP, and shader programming expertise to improve performance outcomes
• ▹Document optimization decisions clearly, noting relevant profiler metrics

Requirements

• ▹Available to work at least 20 hours/week
• ▹Fluent in core C++ features through C++17
• ▹Working knowledge of Python and Git
• ▹Fluent in at least one GPU programming model (CUDA, HIP, Slang, HLSL, or GLSL)
• ▹At least 1 year of professional or graduate-level research experience with GPUs
• ▹Strong understanding of GPU profiler performance metrics for kernel optimization
• ▹Ability to optimize GPU kernels without deep prior context on every algorithm

Nice to have

• ▹Experience with CUDA, HIP, CUDA C++ Core Libraries, inline PTX assembly, or tensor core-level optimization
• ▹Experience optimizing kernels for NVIDIA Blackwell hardware
• ▹Familiarity with NSight Compute
• ▹Prior experience with GPU hardware organizations such as NVIDIA, AMD, or Qualcomm
• ▹Open-source contributions related to GPU kernel optimization

What we offer

• ▹Compensation $80-120/hour
• ▹Remote work

About the company

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, its investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.