GitHub Scholar LinkedIn
001 / Archean · Berkeley Lab

Solving hard
problems with AI,
physics & chemistry.

I'm Théo Jaffrelot Inizan — founder & AI scientist at Archean, and associate researcher at Berkeley Lab. I build AI that understands physics, matter and chemistry — to solve the hardest problems.

Explore research Publications →
Founder, Archean · Associate Researcher, Berkeley Lab
drag to rotate
Materials generated by AI, synthesized in the lab.
T. Jaffrelot Inizan et al. — Nature Computational Science, 2026
002 / About
Portrait of Théo Jaffrelot Inizan

I’m part of the founding team of Archean — founder & AI scientist — and an associate researcher at Lawrence Berkeley National Lab. I build AI models that understand physics and chemistry at every level — from the atomistic scale to predicting real-world experiments — with one goal: solving the hardest problems, from quantum sensing to destroying forever chemicals to pulling CO₂ from air.

Previously, I was a researcher at UC Berkeley and Berkeley Lab, working with Omar Yaghi (Nobel Prize in Chemistry 2025), Kristin Persson, Jennifer Chayes, Christian Borgs and Joseph Gonzalez on generative AI to discover and understand materials science and chemistry.

Before: PhD at Sorbonne University and UT Austin (Fulbright scholar) with Jean-Philip Piquemal and Pengyu Ren · M.Sc. at EPFL in Materials & Computer Science with Nicola Marzari and Clémence Corminboeuf · Engineering degree in Materials Science, Institut National Polytechnique.

Bakar FellowSorbonne PhD ’23FulbrightEPFLUT Austin
UC BerkeleyLawrence Berkeley National LaboratorySorbonne UniversityEPFLUniversity of Texas at AustinVrije Universiteit AmsterdamNVIDIAAmazon Web Services

Expertise

003 / what I work on
— A

Generative AI for Science

New models and architectures that discover materials and chemicals, design experiments, and connect to physical lab environments.

— B

Quantum Mechanics × Machine Learning

Models that fuse machine learning with quantum mechanics and HPC acceleration to predict quantum phenomena at speed — 8+ years building universal models, from photochemistry to reticular materials.

— C

Physical AI

AI for robotics and drones that understands and acts in the 3D world.

Selected work

004 / highlights
01

System of agentic AI for the discovery of metal-organic frameworks

T. Jaffrelot Inizan, S. Yang, A. Kaplan, Y. Lin, J. Yin, S. Mirzaei, M. Abdelgaid, A. H. Alawadhi, K. Cho, Z. Zheng, E. D. Cubuk, C. Borgs, J. T. Chayes, K. A. Persson, O. M. Yaghi
Nat Comput Sci ’26 · accepted 02

Large language models for reticular chemistry

Z. Zheng, N. Rampal, T. Jaffrelot Inizan, C. Borgs, J. T. Chayes, O. M. Yaghi
Nat Rev Mater ’25 03

A universal augmentation framework for long-range electrostatics in machine learning interatomic potentials

D. Kim, X. Wang, S. Vargas, P. Zhong, D. S. King, T. Jaffrelot Inizan, B. Cheng
JCTC ’25 04

uMOF: A Universal Database, Benchmark, and Machine Learning Interatomic Potentials for Metal-Organic Frameworks

T. Jaffrelot Inizan, P. Divakar Kamath, A. Marin Elena, K. A. Persson
NeurIPS ’26 · accepted

Recent publications

005 / 25 total
System of agentic AI for the discovery of metal-organic frameworks Nat. Comput. Sci · accepted uMOF: A Universal Database, Benchmark, and Machine Learning Interatomic Potentials for Metal-Organic Frameworks NeurIPS · accepted Data-driven Design of Metal-Organic Frameworks with Tunable Negative Thermal Expansion J. Am. Chem. Soc · 2026 All publications & talks →

In the lab & beyond

006 / moments
Portrait Research event at UC Berkeley
007 / Contact

Don’t hesitate to reach out.

Always happy to talk AI, chemistry and materials — questions about MOFGen, the papers, or anything in between.

Google ScholarGitHubLinkedInX / Twitter