Experienced CUDA/C++ Developer - Remote Long-Term Collaboration -- 2
Publicada el 2026-07-28
Descripción de la oferta
CUDA Developer Needed – Long-Term Remote Task-Based Work (AnyDesk/Remote Access) I am looking for an experienced CUDA/C++ developer to help complete GPU optimization and debugging tasks. This is a long-term collaboration opportunity for someone with strong experience in CUDA kernels, PyTorch, and GPU performance optimization. Work Setup: This is a task-based job. Each task requires approximately 3 hours of focused work. Developers can take up to 3 tasks per day (maximum 9 hours/day) depending on availability. Maximum workload can reach up to 40 hours per week for active developers. You will work directly on my development environment through AnyDesk, TeamViewer, or another preferred remote desktop connection. You must be comfortable working directly from your PC using remote access. Tasks involve debugging, improving, optimizing, and validating CUDA implementations. Please read the project requirements and task instructions carefully before bidding. This is not a one-time project; it is intended to become a long-term working relationship with regular CUDA tasks for the right developer. Payment: Rate: $8–$10 per hour depending on experience. Payment will be released after 2 weeks for the (1st payment after that it will be every friday gmt -8 3pm)of completed work. Consistent developers will receive ongoing tasks. Required Skills: Strong C++ programming skills. Professional experience with CUDA kernel development. Understanding of: GPU memory optimization. CUDA streams. Kernel performance tuning. Parallel programming concepts. Experience debugging CUDA correctness issues. Knowledge of PyTorch CUDA extensions is a plus. Experience with: Linux environments. Git/GitHub workflows. GPU benchmarking and profiling tools. Current Types of Tasks: Fix CUDA kernel correctness issues. Compare custom CUDA implementations against PyTorch reference implementations. Debug: Tensor indexing problems. Convolution operations. Normalization layers. Residual connections. Optimize GPU performance after correctness is achieved. Run benchmarks and analyze kernel performance. To Apply, Please Provide: Your CUDA/C++ development experience. Examples of CUDA projects or GPU optimization work you have completed. Your hourly availability and how many tasks you can handle per day. Your preferred remote access method (AnyDesk, TeamViewer, or other). Confirm that you can work directly from your PC through remote connection. Important: Only apply if you have real CUDA/C++ experience and can follow technical instructions carefully. Developers must review the project requirements before bidding. This can become a long-term remote position with continuous CUDA optimization tasks for the right developer.
Skills
Fuente original: freelancer