Computational materials scientist. I work at Periodic Labs on high-throughput density functional theory (DFT) and machine-learning force fields (MLFFs)
for atomistic simulations.
Widely used Python library for materials analysis, from crystal structures and symmetry to phase diagrams and I/O for most DFT codes. Powers the Materials Project.
First-principles MD benchmark testing foundation MLIPs on structural and dynamical observables at finite temperature. Powers the MD leaderboard on Matbench Discovery.
Widely used database, website, API and OSS ecosystem built for computing properties of inorganic materials.
Benchmark for machine learning energy models simulating a real-world materials discovery campaign.
A foundational DFT potential energy dataset for materials covering 89 elements and emphasizing data diversity and quality (at PBE and r2SCAN level).
Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning
Torch-native engine for batched atomistic simulations, running molecular dynamics, relaxations and MLIP inference on many systems at once on GPUs.
Pushing the Pareto front of band gap and permittivity with ML-guided dielectrics discovery incl. experimental synthesis.
Benchmarking ML models for materials discovery, ML-guided dielectrics search and the MACE-MP foundation model.
A library of Svelte components for building interactive web apps with performant chemistry visualizations like periodic tables, Bohr atoms, nuclei, heatmaps, scatter plots.
A toolkit for visualizations in materials informatics to complement pymatgen.
Keyboard-friendly, accessible and customizable Svelte components incl. MultiSelect, Toc, PageSearch and more.
atomate2 is a library of computational materials science workflows used by the Materials Project and beyond.
Pretrained universal neural network potential for charge-informed atomistic modeling published on the Sep 2023 cover of NMI.
Curated list of resources for learning and using normalizing flows, a powerful tool in ML for modeling probability distributions.
Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.
This is a compilation of notes and solutions to problem sheets for some of the physics lectures I took, most of them in Heidelberg. Hopefully, they can be useful to others. If you find errors, please open an issue.