Xiaoliang Pan
Founding Member Of Technical Staff at Stealth AI Startup
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolXiaoliang Pan is a founding member of technical staff at a stealth AI startup in New York with 13 years of experience translating physics-grounded molecular theory into production-ready modeling, ML, and scientific software. He has a PhD in physical chemistry and a long academic-to-industry trajectory—spanning postdoctoral research on equivariant ML potentials, QM/MM electrostatics, and enzyme design—now focused on zero-to-one technical execution and high-stakes architecture decisions. Xiaoliang pairs deep domain expertise with hands-on engineering: notable open-source contributions include backend fixes to the widely used ParmEd molecular toolkit, improving topology handling and netCDF data robustness. He excels at turning advanced theory into scalable systems that accelerate reliable discovery and enjoys collaborating with builders at the computation–science frontier.
13 years of coding experience
13 years of employment as a software developer
Doctor of Philosophy (PhD) Physical Chemistry, Doctor of Philosophy (PhD) Physical Chemistry at Jilin University
Chinese, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (7)
molecular-simulation10
python10
scientific-computing10
data-structure9
data-structures9
develop8
numpy7
Programming languages (8)
Github contributions (5)
ParmEd/ParmEd
Oct 2017 - Jun 2018
Parameter/topology editor and molecular simulator
Role in this project:
Back-end Developer
Back-end DeveloperContributions:6 commits, 3 PRs, 2 comments in 7 months
Contributions summary:Xiaoliang primarily contributed to the project by fixing bugs and making improvements to existing functionality. Their work involved modifying core data structures and functions within the `parmed` library, particularly focusing on bond deletion and data handling in tools and parameter sets. Furthermore, the user addressed issues related to how certain properties, such as velocities and box information, were accessed and handled within the netcdf files.
physicslammpssimulationmolecularparameter
panxl/torchmd-net
Sep 2023 - Mar 2024
Neural network potentials based on graph neural networks and equivariant transformers
Contributions:1 PR, 68 pushes, 1 branch in 5 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.