Janosh Riebesell - CV
I worked for the Materials Project from Jul 2022 to Dec 2023 where I developed ML foundation models (CHGNet, MACE-MP) and high-throughput workflows for generating more diverse, higher-quality DFT datasets for future models.
In April 2024, I joined Radical AI to vertically integrate MLIPs and robotic labs.
I contribute to open source projects and help maintain matbench-discovery
, torch-sim
, pymatgen
, pymatviz
, atomate2
. See the full list.
Publications Sort by
Atomate2: modular workflows for materials science
A. Ganose, ..., J. Riebesell, ..., A. Jain — 10.1039/D5DD00019J — Digital Discovery — 2025-7Accelerated data-driven materials science with the Materials Project
M. Horton, ..., J. Riebesell, ..., K. Persson — 10.1038/s41563-025-02272-0 — Nature Materials — 2025-7Matbench Discovery - A framework to evaluate machine learning crystal stability predictions
J. Riebesell, R. Goodall, ..., K. Persson — 10.1038/s42256-025-01055-1 — Nature Machine Intelligence — 2025-6A Foundational Potential Energy Surface Dataset for Materials
A. Kaplan, ..., J. Riebesell, ..., S. Ong — 10.48550/arXiv.2503.04070 — 2025-3Developments and applications of the OPTIMADE API for materials discovery, design, and data exchange
M. Evans, ..., J. Riebesell, ..., R. Armiento — 10.1039/D4DD00039K — Digital Discovery — 2024-8Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning
B. Deng, ..., J. Riebesell, ..., G. Ceder — arxiv.org/abs/2405.07105 (preprint) — 2024-5LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation
Y. Chiang, C. Chou, J. Riebesell — arxiv.org/abs/2401.17244 (preprint) — 2024-1Pushing the Pareto front of band gap and permittivity: ML-guided search for dielectric materials
J. Riebesell, T. Surta, ..., A. Lee — arxiv.org/abs/2401.05848v1 (preprint) — 2024-1Jobflow: Computational Workflows Made Simple
A. Rosen, ..., J. Riebesell, ..., A. Ganose — 10.21105/joss.05995 — Journal of Open Source Software — 2024-1A foundation model for atomistic materials chemistry
I. Batatia, ..., J. Riebesell, ..., G. Csányi — arxiv.org/abs/2401.00096v1 (preprint) — 2023-12CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling
B. Deng, ..., J. Riebesell, ..., G. Ceder — 10.1038/s42256-023-00716-3 — Nature Machine Intelligence — 2023-9Crystal Toolkit: A Web App Framework to Improve Usability and Accessibility of Materials Science Research Algorithms
M. Horton, ..., J. Riebesell, ..., K. Persson — 10.48550/arXiv.2302.06147 — 2023-2
Open Source Sort by
pymatgen 1668 ⭐ 1048 commits Python, Cython
One of the largest and most popular open source materials analysis codes that defines classes for structures, molecules, slabs, etc. and interfaces seamlessly with various other materials codes. It also powers the Materials Project.
Matbench Discovery 165 ⭐ 463 commits Python, TypeScript, Svelte
Benchmark for machine learning energy models simulating a real-world materials discovery campaign.
pymatviz 235 ⭐ 423 commits Python, Svelte, CSS
A toolkit for visualizations in materials informatics to complement pymatgen.
atomate2 223 ⭐ 379 commits Python, Jupyter Notebook, Shell
atomate2 is a library of computational materials science workflows used by the Materials Project and beyond.
MultiSelect 322 ⭐ 288 commits TypeScript, Svelte, CSS
Keyboard-friendly, accessible and customizable multi-select web component.
Scientific Diagrams 325 ⭐ 251 commits Typst, TeX, Svelte
[Typst](https://typst.app) and [LaTeX](https://www.latex-project.org) diagrams of concepts in physics/chemistry/ML.
MatterViz 158 ⭐ 241 commits TypeScript, Svelte, CSS
A library of Svelte components for building interactive web apps with performant chemistry visualizations like periodic tables, Bohr atoms, nuclei, heatmaps, scatter plots.
Aviary 57 ⭐ 237 commits Python
Compositional, structural and coarse-grained structural ML energy model implementations (Roost, Wren, CGCNN, Wrenformer) with a consistent API.
CHGNet 313 ⭐ 196 commits Python, C, Cython
Pretrained universal neural network potential for charge-informed atomistic modeling published on the Sep 2023 cover of NMI.
jobflow 104 ⭐ 136 commits Python, TeX
jobflow is a library for writing computational workflows. It provides the plumbing underlying atomate2 and was adopted by several other workflow libraries.
Tensorboard Reducer 74 ⭐ 85 commits Python, TeX
Reduce multiple PyTorch TensorBoard runs to new events/CSV/JSON. Good for model ensembles.
MatCalc 95 ⭐ 77 commits Python, Jupyter Notebook
A Python library for calculating materials properties from ML force field potential energy surfaces.
Normalizing Flows 1541 ⭐ 74 commits Python
Curated list of resources for learning and using normalizing flows, a powerful tool in ML for modeling probability distributions.
MLIP PES softening 21 ⭐ 61 commits Python, CSS, Svelte
Overcoming systematic softening in universal machine learning interatomic potentials by fine-tuning
TorchSim 244 ⭐ 30 commits Python
Torch-native, batchable, atomistic simulation.
Dielectrics 10 ⭐ 27 commits HTML, Python, TeX
Pushing the Pareto front of band gap and permittivity with ML-guided dielectrics discovery incl. experimental synthesis.
MACE Foundation Models 22 commits message, documentation_url, status
Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.
MatPES 38 ⭐ Jupyter Notebook, Python, CSS
A foundational DFT potential energy dataset for materials covering 89 elements and emphasizing data diversity and quality (at PBE and r2SCAN level).
Materials Project message, documentation_url, status
The Materials Project is a database of computed properties for inorganic materials.
Education
PhD Student - University of Cambridge
Thesis title: Towards Machine Learning Foundation Models for Materials ChemistryMPhil in Scientific Computing - University of Cambridge
Thesis title: Probabilistic Data-Driven Discovery of Thermoelectric MaterialsMSc in Physics - ITP Heidelberg
Thesis title: Functional Renormalization Group Analytically Continued to Finite TemperaturesBSc in Physics - Hamburg University
Thesis title: van der Waals Corrections for Density Functional Theory - DFT+D2 applied to Graphene-hBN-Heterostructures
Languages
- English
- German
- French
- Spanish
Nationality
- Canadian
- German
Programming Languages and Tools
(emphasis ≈ proficiency)- Python (10)
- TypeScript (10)
- JavaScript (10)
- Svelte (10)
- Node.js (9)
- MongoDB (8)
- PyTorch (8)
- Dash (8)
- React (8)
- Deno (8)
- vitest (8)
- Puppeteer (8)
- PlayWright (8)
- REST (7)
- Git (6)
- TensorFlow (6)
- GraphQL (5)
- Mathematica (4)
- JAX (4)
- C (3)
Memberships
- Cambridge Physical Society 2019 - present
- Materials Research Society 2023 - present
- Materials Project Software Foundation 2023 - present
Hobbies
- photography
- video editing
- hiking
- cycling
- climbing
- drones