Matrix Multiply-Accumulate (Tensor Core) Project -- 2

I am looking for someone to work on a Matrix Multiply-Accumulate (Tensor Core) for CPU and GPU Project. Must understand CUDA, Tensor Core, Parallel Processing, Parallel Computing and good at Python and C/C++ programming. Must be expert in CS, Jupyter notebook, numerical libraries, performance optimization, parallelization Python infrastructure, parallel programing and parallel I/O for heterogeneous storage systems. Several Projects will follow for the right person.