John Dagdelen
Founder at Fluid.so
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolJohn Dagdelen is a founder and computational materials scientist turned spatial-computing entrepreneur in San Francisco, combining 10 years of research and engineering experience with hands-on product building at Fluid. He earned a PhD from UC Berkeley applying machine learning and LLMs to materials discovery, and has contributed to influential open-source materials tooling such as pymatgen, signaling deep domain knowledge in materials analysis and scientific software. His background includes internships and research roles at Google Brain, Berkeley Lab, and NREL, where work ranged from ML-driven property prediction to high-throughput materials screening and even a patent-pending investigation on perovskite stability. At Fluid he’s translating complex spatial and ML concepts into accessible products, bringing both academic rigor and pragmatic engineering to early-stage product development.
10 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD Computational Materials Science, Doctor of Philosophy - PhD Computational Materials Science at University of California, BerkeleyHigh School, High School at Robert College
English, Turkish, Spanish
Stackoverflow
41reputation
2kreached
3answers
1question
Github Skills (5)
pymatgen10
python10
materials-informatics10
mathematical-optimization6
plot6
Programming languages (12)
Github contributions (5)
materialsproject/pymatgen
Apr 2017 - Aug 2018
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:
Back-end Developer
Back-end DeveloperContributions:13 commits, 3 PRs, 7 comments in 1 year 4 months
Contributions summary:John's contributions primarily focused on improvements and bug fixes within the pymatgen library, specifically related to the `JmolNN` class, indicating expertise in materials analysis algorithms. They corrected the spelling of "Jmol" and removed a redundant constant. Additionally, the user was involved in merging updates from the master branch and adding minimum bond distance in the `JmolNN` class, demonstrating maintenance and feature enhancement activities. This work reflects a focus on refining the core functionality of the materials science software.
moleculespythonscienceelectronic-structurepowers
jdagdelen/hyperDB
Apr 2023 - Feb 2025
A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $135M cap.
Contributions:1 release, 7 reviews, 14 PRs in 1 year 10 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.