Experienced CUDA/C++ Developer - Remote Long-Term Collaboration
Publicada el 2026-07-28
Descripción de la oferta
CUDA Developer Needed – Long-Term Remote Work (AnyDesk/Remote Access) I am looking for an experienced CUDA/C++ developer to help me complete GPU optimization tasks. This is a long-term collaboration opportunity for someone with strong experience in CUDA kernels, PyTorch, and performance optimization. Work setup: Remote work through AnyDesk or another remote desktop tool. You will work directly on my development environment. Tasks involve debugging, improving, and optimizing CUDA implementations. Each task typically requires around 3 hours of focused work. Payment: Rate: $8–$10 per hour depending on experience. Payment will be released after 2 weeks of completed work. This is intended to become a long-term working relationship with regular tasks. Required skills: Strong C++ programming skills. CUDA kernel development experience. Understanding of GPU memory optimization, CUDA streams, and kernel performance. Experience debugging CUDA correctness issues. Knowledge of PyTorch CUDA extensions is a plus. Experience with Linux, Git, and benchmarking tools. Current type of tasks: Fix CUDA kernel correctness issues. Compare CUDA implementations against PyTorch reference implementations. Debug tensor indexing, convolution operations, normalization layers, and residual connections. Optimize GPU performance after correctness is achieved. To apply, please provide: 1. Your CUDA/C++ experience. 2. Examples of CUDA projects you have completed. 3. Your hourly availability. 4. Your preferred remote access method. This can become a long-term position for the right developer.
Skills
Fuente original: freelancer