GPU Kernel Optimizer for AI Performance (CUDA/C++)

Mercor; Chicago (IL); On-site; USD 83,000 - 165,000; Part time

Job summary

Mercor is seeking GPU kernel optimization experts to contribute to a project with a leading AI lab. This contract-based opportunity targets freelancers with strong C++ skills, practical GPU programming experience, and the ability to improve kernel performance through profiler-guided analysis.

You will analyze, optimize, and reason about GPU kernels across modern hardware environments, writing C++17 and Python code while applying CUDA, HIP, or related kernel programming techniques to drive

Qualifications

• Available to work at least 20 hrs/wk.
• Fluent in core C++ features through C++17.
• Working knowledge of Python and Git.
• Fluent in at least one GPU programming model such as CUDA or HIP.
• At least 1 year of GPU-related experience.
• Strong understanding of GPU profiler metrics for optimization.
• Ability to optimize kernels without deep prior context.
• Experience with CUDA, HIP, inline PTX, or tensor core optimization is a plus.
• Experience optimizing kernels for NVIDIA Blackwell hardware is a plus.
• Familiarity with NSight Compute is a plus.
• Prior GPU hardware experience with NVIDIA/AMD/Qualcomm is a plus.

Responsibilities

• Analyze and optimize GPU kernels for performance and hardware utilization.
• Use profiler metrics to guide kernel improvements.
• Review GPU kernel implementations and identify bottlenecks.
• Write and modify C++17, Python, and GPU programming code.
• Apply CUDA, HIP, or related kernel programming to improve performance.
• Document optimization decisions clearly.

Skills

C++17

Python

GPU programming

CUDA

HIP

NSight Compute

Git

Profiler metrics

Tools

CUDA toolkit

Inline PTX

Tensor cores

Job description

Mercor is seeking GPU kernel optimization experts to contribute to a project with a leading AI lab. This contract-based opportunity targets freelancers with strong C++ skills, practical GPU programming experience, and the ability to improve kernel performance through profiler-guided analysis.

You will analyze, optimize, and reason about GPU kernels across modern hardware environments, writing C++17 and Python code while applying CUDA, HIP, or related kernel programming techniques to drive