Freelance GPU Kernel Optimizer - CUDA/C++ Specialist

Obsidian; San Francisco (CA); Remote; USD 90,000 - 130,000; Part time

Job summary

Obsidian is seeking GPU kernel optimization experts to work with a leading AI lab. The role involves analyzing and optimizing GPU kernels for improved performance and efficiency, ideally suited for freelancers with strong C++ skills and GPU programming experience.

Qualified candidates will document optimization processes and work a minimum of 20 hours per week, focusing on enhancing performance for modern GPU architectures.

Qualifications

• Fluent in core C++ features through C++17.
• At least 1 year of professional or graduate-level research experience working with GPUs.
• Strong understanding of GPU profiler performance metrics.

Responsibilities

• Analyze and optimize GPU kernels for performance and efficiency.
• Use profiler metrics to guide kernel improvements.
• Write, modify, and reason about C++17 and GPU programming code.

Skills

GPU kernel optimization

C++17

CUDA

Python

Git

Tools

NSight Compute

CUDA C++ Core Libraries

Job description

Obsidian is seeking GPU kernel optimization experts to work with a leading AI lab. The role involves analyzing and optimizing GPU kernels for improved performance and efficiency, ideally suited for freelancers with strong C++ skills and GPU programming experience.

Qualified candidates will document optimization processes and work a minimum of 20 hours per week, focusing on enhancing performance for modern GPU architectures.