Oscar Huguet is a CUDA Edge Computing Tech Lead with 14 years of experience accelerating and productionizing scientific and industrial codes for real-time video, computer vision and deep learning applications. He specializes in porting, optimizing and tuning existing CPU/GPU codebases using CUDA, OpenCL, OpenMP, GCD and HSA, while preserving original functionality and scaling to multi-GPU edge servers. At Mediapro he leads a C++/CUDA team delivering realtime multi-camera capture, processing and encoding for the AutomaticTV product and collaborates on performance improvements to major open-source projects. He also teaches parallel programming at the University of Barcelona, bridging academic rigor with hands-on engineering. Notably, his background includes building tooling that mixes assembler and C++ templates and adapting C++ libraries for new GPU languages, reflecting a deep bent for pragmatic low-level optimization.
14 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Architecture, Doctor of Philosophy - PhD, Computer Architecture at Universitat Politecnica de Catalunya
Computer engineering, Ingeniería Tecnica Informatica de Sistemas, Computer engineering, Ingeniería Tecnica Informatica de Sistemas at Universitat de Barcelona / University of Barcelona
This project is a place to put all my tests, looking into better understanding CUDA, and GPU performance behavior. There might also be some exercise descriptions to teach CUDA and parallel programming.
Contributions:67 commits, 1 PR, 62 pushes in 3 years 6 months
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.
Request Free Trial
Oscar Huguet - CUDA Edge Computing Tech Lead at AutomaticTV