Evan Weinberg
Senior Compute DevTech Engineer at NVIDIA
Watertown, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolEvan Weinberg is a Senior Compute DevTech Engineer at NVIDIA with 12 years of experience accelerating scientific workloads from single workstations to the largest supercomputers. He specializes in GPU optimization for molecular dynamics and lattice QCD, contributing high-impact performance work such as SNAP kernel refactors in the widely used LAMMPS codebase. A Ph.D. in Physics and postdoctoral experience in exascale algorithm development inform his focus on tailored preconditioners and multiscale solvers for sparse linear systems. He was part of a Gordon Bell finalist team at SC21, demonstrating an ability to translate cutting-edge research into record-class HPC performance. Based in Watertown, MA, Evan blends deep physics intuition with hands-on GPU engineering to push domain science onto modern accelerator architectures. Colleagues rely on him for pragmatic, low-level optimizations that materially reduce GPU memory usage and runtime in production scientific codes.
11 years of coding experience
3 years of employment as a software developer
Master of Science (M.S.), Physics, 4.0, Master of Science (M.S.), Physics, 4.0 at Rensselaer Polytechnic InstituteDoctor of Philosophy (Ph.D.), Physics, Doctor of Philosophy (Ph.D.), Physics at Boston University
English
Github Skills (9)
cuda10
c-language10
molecular-dynamics-simulation10
parallel-computing10
cprogramming-language10
performance-optimization10
molecular-simulation10
k10
dynamics10
Programming languages (5)
Github contributions (5)
lammps/lammps
Mar 2020 - Oct 2022
Public development project of the LAMMPS MD software package
Role in this project:
Back-end Developer
Back-end DeveloperContributions:19 reviews, 28 commits, 11 PRs in 2 years 7 months
Contributions summary:Evan contributed significantly to the performance optimization of the LAMMPS molecular dynamics software, specifically focusing on the SNAP (Spectral Neighbor Analysis Potential) pair style. The commits involve refactoring and optimizing the core routines, particularly those utilizing the Kokkos library for GPU acceleration. These optimizations include code improvements for kernel fusion, reducing memory usage on the GPU, and improving the efficiency of the calculations within the SNAP kernels.
lammpsmolecular-dynamicssimulationkokkos
weinbe2/quantum-mg
Dec 2017 - Dec 2022
Contributions:8 pushes in 5 years
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.