Logan Ward
Senior Application Engineer
Atlanta, Georgia, United States
Summary
👤
Senior🎓
Top SchoolLogan Ward is a senior application engineer and computational materials scientist with 12 years of experience building AI-for-science tools and production-ready software, now applying that expertise at NVIDIA on GenAI and advanced computing hardware. He spent six years at Argonne National Lab designing machine learning methods to accelerate materials discovery and creating infrastructure to make those capabilities accessible to researchers. A frequent open-source contributor, Logan has improved core materials libraries such as pymatgen and advanced atomistic ML frameworks like SchNetPack and MEGNet, adding features, tests, and performance-minded tooling. He blends deep domain knowledge in materials science (PhD, Northwestern) with practical ML engineering—often translating research ideas into robust, unit-tested code used by the community. Based in Atlanta, he’s also an educator and boardgame enthusiast, reflecting a curiosity-driven approach to complex problems.
12 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Materials Science and Engineering, Doctor of Philosophy (Ph.D.), Materials Science and Engineering at Northwestern UniversityMaster’s Degree, Materials Science and Enginnering, Master’s Degree, Materials Science and Enginnering at The Ohio State University
Github Skills (42)
unit-testing10
pytorch10
python10
scikit10
rdkit10
machine-learning10
bash10
python-multiprocessing10
affinity10
environment-variables10
materials-informatics10
linear-models10
hyperparameter-optimization10
openmp10
parallel-processing10
Programming languages (10)
Github contributions (5)
materialsproject/pymatgen
Dec 2017 - Oct 2019
Python Materials Genomics (pymatgen) is a robust materials analysis code that defines classes for structures and molecules with support for many electronic structure codes. It powers the Materials Project.
Role in this project:
Backend Developer
Backend DeveloperContributions:37 commits, 13 PRs, 15 comments in 1 year 10 months
Contributions summary:Logan primarily contributed to the `pymatgen` library, focusing on the `analysis` module, particularly the `EwaldSummation` class. Their work involved implementing new features for calculating site energies, adding charged cell corrections, and improving the accuracy of energy calculations. The user also made significant contributions to unit tests, ensuring the correctness and reliability of the implemented functionalities. Furthermore, the user added new methods to the `Composition` class for handling oxidation states.
moleculespythonscienceelectronic-structurepowers
atomistic-machine-learning/schnetpack
Jan 2019 - Mar 2021
SchNetPack - Deep Neural Networks for Atomistic Systems
Role in this project:ML Engineer
ML EngineerContributions:6 commits, 6 PRs, 3 comments in 2 years 1 month
Contributions summary:Logan primarily contributed to the project by addressing issues and enhancing the functionality of the SchNetPack deep learning framework. Their work involved fixing problems related to subset handling, adding new features like MaxAggregation and SoftmaxAggregation layers to the neural network base, and improving the documentation for atomref. These modifications suggest the user's focus on refining the core components and usability of the deep learning models within the SchNetPack framework.
condensed-mattermolecular-dynamicsatomistic-systemsdeep-learningtorch
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.