Attila Krasznahorkay is an experimental particle physicist and software researcher with 18 years of experience building high-performance offline and analysis software for large-scale experiments, most recently as Convener of the Analysis Software Group for ATLAS at CERN and now a researcher at UMass Amherst. He combines deep domain expertise in track reconstruction and analysis with hands-on C++ and CUDA development—contributing key CUDA SeedFinder implementations and kernel optimizations to the widely used ACTS tracking toolkit and improving build and linking robustness in the ROOT data framework. Comfortable at the intersection of research and engineering, he has led collaborative software efforts across international teams and architectures, including SYCL/CUDA portability work and careful device memory management. His background — a PhD in Experimental Particle Physics from the University of Debrecen and long-term roles at CERN and NYU — gives him a rare ability to translate complex physics requirements into performant, production-ready code.
18 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Experimental Particle Physics, Doctor of Philosophy (Ph.D.), Experimental Particle Physics at University of Debrecen
The official repository for ROOT: analyzing, storing and visualizing big data, scientifically
Role in this project:
Backend & Build Engineer
Contributions:4 reviews, 16 commits, 14 PRs in 4 years 4 months
Contributions summary:Attila primarily focused on improving the build process and configuration of the ROOT project, particularly concerning the use of external libraries. They addressed issues related to the GSL and libatomic libraries, ensuring correct linking and usage within the build system. These changes included modifying the CMake build scripts, introducing new variables, and fixing typos to enhance build compatibility and efficiency, especially on specific architectures. The contributions ensured proper integration of external libraries and compatibility of the project.
Experiment-independent toolkit for (charged) particle track reconstruction in (high energy) physics experiments implemented in modern C++
Role in this project:
Backend Developer
Contributions:82 reviews, 6 commits, 11 PRs in 1 year 2 months
Contributions summary:Attila's contributions focused on enhancing the CUDA plugin for particle track reconstruction, a key component of the repository's function. They added a second CUDA-based SeedFinder implementation, refactored SYCL-related code, and improved CUDA device memory management. The user's work involved implementing and optimizing CUDA kernels for tasks like coordinate transformation and triplet finding, which are critical for efficient track reconstruction in high-energy physics experiments.
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
Attila Krasznahorkay - Researcher at University of Massachusetts Amherst