Richard Berger
Scientist 3 at Los Alamos National Laboratory
Los Alamos, New Mexico, United States
Summary
🤩
Rockstar🎓
Top SchoolRichard Berger is a High-Performance Computing specialist and research software engineer with 13 years of experience optimizing computational science codes and building shared HPC infrastructure. He holds a PhD in Mechatronics and progressed from academic research on DEM/LIGGGHTS to core developer work on the widely used LAMMPS molecular dynamics code. At Temple and Los Alamos he has led procurements, deployed and configured large clusters (including a 6,500+ core Owl’s Nest), introduced CI and GitHub workflows, and manages GPU servers for ML workloads. His open-source contributions span package management and deployment tooling—visible in work on spack and cobbler—plus back-end and CI improvements that ease complex scientific builds. He regularly teaches and runs hands-on HPC courses abroad, translating low-level performance tuning into reproducible, maintainable software practices. Colleagues rely on him for pragmatic optimizations that uncover algorithmic bottlenecks rather than relying solely on raw hardware.
13 years of coding experience
14 years of employment as a software developer
Diplomingenieur, Mechatronics, Diplomingenieur, Mechatronics at Johannes Kepler Universität Linz
English, Spanish, German
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (20)
fedora10
docker10
package-management10
python10
scripting10
centos10
hpc10
cmake10
dockers10
script10
build-automation10
sh10
shell10
deploying9
cicd9
Programming languages (11)
Github contributions (5)
spack/spack
Mar 2022 - Jan 2023
A flexible package manager that supports multiple versions, configurations, platforms, and compilers.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:206 reviews, 23 commits, 130 PRs in 10 months
Contributions summary:Richard primarily contributed to the development of the `spack/spack` package manager by creating and updating package definitions. They added new packages like `ports-of-call`, `spiner`, `flcl`, `singularity-eos`, and others, while also adding new versions to existing packages. The user also fixed issues related to CUDA and dependencies, such as those related to the `flecsi` and `legion` packages. These modifications and improvements likely involve back-end logic to support building software packages with complex configurations.
compilerspythonradiussplatformslinux
cobbler/cobbler
Oct 2019 - Nov 2019
Cobbler is a versatile Linux deployment server
Role in this project:DevOps Engineer
DevOps EngineerContributions:33 commits, 7 PRs, 15 comments in 27 days
Contributions summary:Richard's contributions primarily focused on improving the build and deployment infrastructure for the project. They created and modified Dockerfiles for various CentOS and Fedora versions, adding dependencies and addressing issues with image builds. They also streamlined the CI/CD pipeline using shell scripts, and fixed an issue in tftpgen.py.
tftppythondeploymentlinuxdocker
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.