Adrian Shvay is a senior MTS and hardware-aware software engineer with over a decade of production C++ expertise and deep specialization in GPU architectures, GPGPU techniques, and numerical methods. He has led design and implementation of performance-critical deep learning stacks and custom frameworks—integrating PyTorch/TensorFlow with accelerator APIs and architecting multithreading and SIMD/AVX512 optimizations for Intel’s neural-network and Gaudi hardware. His background spans OpenCL/CUDA, OpenGL, assembler-level tuning and CPU/GPU interoperability, with a track record of shipping codec and image-processing accelerations at AMD and Intel. Known for squeezing performance from both hardware and software, he combines strong mathematical intuition (3D geometry, numerical methods) with hands-on low-level optimization. Based in Gdańsk, he now applies that mix of systems-level thinking and DL tooling experience to advancing next-generation AI accelerators.
10 years of coding experience
14 years of employment as a software developer
Ukrainian Lyceum of Physics and Mathematics of T. Schevchenko Kiev University
Department of Telecommunicational radio electronics and electronic engineering, Department of Telecommunicational radio electronics and electronic engineering at National University “Lvivska Politechnika“
Master of Science Physics, Master of Science Physics at Ivan Franko Lviv National University
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.