Role OverviewApply expertise as a GPU programmer to design GPU-related tasks to train LLMs, focusing on performance and architecture.
What You Will Do
Design, implement, and optimize GPU-based software solutions using CUDA, WebGPU or GLSL, profile and fine-tune GPU kernels and shaders for maximum performance and efficiency, develop host-side logic and integrations in C++.
Why It Might Be a Fit
Advanced experience with any GPU programming language that can run on NVIDIA chips, background in either Graphics Programming, ML acceleration, Scientific Computing, High Performance Computing, or any other domain using GPU technologies, proficiency in C++.
Requirements
- Advanced experience with any GPU programming language that can run on NVIDIA chips
- Background in either Graphics Programming, ML acceleration, Scientific Computing, High Performance Computing, or any other domain using GPU technologies
- Proficiency in C++
Benefits
- Output-based compensation; experts are paid per task that meets the project specifications
]]>