I will accelerate your code using cuda, c, cpp or python

I am a software developer specializing in High Performance Computing, CUDA kernel programming, Python and C++ performance optimization. I help researchers, developer and data engineers accelerate compute intensive tasks using parallel hardware architectures.

What I Can do for you:

• Custom CUDA C/C++ kernels for GPU Acceleration
• Identify compute and memory bottlenecks using Nsight
• Port slow loops and algorithms to parallel execution
• Shared memory management, coalesced memory access and warp divergence minimization
• Accelerate matrix operations, numerical simulations, image processing and ML pre-processing.

Why work with me?

• Clean, production ready and well commented code
• Clear before and after speedup benchmarks
• Fast turnaround and clear technical communication.

Please send me a message with your code/requirements before placing an order so we can discuss optimal architecture.