AI Forge

Accelerating scientific discovery with AI.

About us

Scientific discovery is a continuous cycle of hypothesis, experimentation, critique, and refinement—a process that often takes researchers months or years. In collaboration with Google Research and Google DeepMind, we developed Co-Scientist: a multi-agent AI system designed to generate and refine breakthrough scientific theories.

“Every breakthrough starts with the right idea. Co-Scientist is a multi-agent AI system, built with Gemini models, that is inspired by the scientific process: it proposes hypotheses grounded in the literature, subjects them to virtual peer review and computational analysis, and runs them through a tournament of ideas until the most promising, testable leads rise to the top. Published in Nature. Validated in the lab.”
0. Matthias Heiler
Matthias Heiler
Distinguished Engineer, AI and Systems Research • Google AI & Infrastructure

Featured research

Accelerating Scientific Discovery with Co-Scientist
Nature 2026

Accelerating Scientific Discovery with Co-Scientist

Juraj Gottweis, Wei-Hung Weng, Alexander Daryin, Tao Tu, Petar Sirkovic, Artiom Myaskovsky, Grzegorz Glowaty, Felix Weissenberger, Alessio Orlandi, Dan Popovici, Anil Palepu, Keran Rong, Ryutaro Tanno, Khaled Saab, Fan Zhang, Jacob Blum, Andrew Carroll, Kavita Kulkarni, Nenad Tomašev, Dina Zverinski, Ivor Rendulic, Elahe Vedadi, Florian Hasler, Luka Rimanic, Marina Boia, Ivan Budiselic, Ben Feinstein, Mathias Bellaiche, Tom Sheffer, Jan Freyberg, Jeremy Ratcliff, Ottavia Bertolli, Katherine Chou, Avinatan Hassidim, Burak Gokturk, Amin Vahdat, Yuan Guan, Vikram Dhillon, Eeshit Dhaval Vaishnav, Byron Lee, Tiago R. D. Costa, José R. Penadés, Gary Peltz, Yossi Matias, James Manyika, Demis Hassabis, Yunhan Xu, Pushmeet Kohli, Annalisa Pawlosky, Alan Karthikesalingam & Vivek Natarajan.

Collaborations

bioRxiv 2026

AI-Guided Discovery of Atypical Protein Assemblies

AmirAli Toghani, Benjamin A. Seager, Yu Sugihara, Lisa-Marie Roijen, Juan M. Azcue, Maián Garro, Maryam Sargolzaei, Ioanna Morianou, Adeline Harant, Sam Gallop, Jiorgos Kourelis, Dan MacLean, Mauricio P. Contreras, Sophien Kamoun, and Daniel Lüdke.

AI-Guided Discovery of Atypical Protein Assemblies

arXiv 2026

Extremal Chowla Sets and Their Linear Analogues: A Human-AI Mathematical Investigation Using Co-Scientist

Mohsen Aliabadi, Keith Driscoll, Elliot Krop, Petar Sirkovic, Everett Sullivan, Elahe Vedadi

Extremal Chowla Sets and Their Linear Analogues: A Human-AI Mathematical Investigation Using Co-Scientist

bioRxiv 2026

Perturb-ME: Scalable Mechanism Discovery from Phenotype-Enriched Genome-Wide Screens

Hanchen Wang, Jiacheng Gu, Chris J. Frangieh, Michael S. Cuoco, Maryann Zhao, Arindam Sett, Tom Beyer, Kuan Pang, Etzard Stolte, Zihan Xu, Jure Leskovec, Orit Rozenblatt-Rosen, Vivek Natarajan, Kathryn Geiger-Schuller, Pratiksha I. Thakore, Aviv Regev

Perturb-ME: Scalable Mechanism Discovery from Phenotype-Enriched Genome-Wide Screens

Some of our people

Matthias Heiler

Matthias Heiler

Software Engineer

Alessio Orlandi

Alessio Orlandi

Software Engineer

Alexander Daryin

Alexander Daryin

Software Engineer

Dina Zverinski

Dina Zverinski

Software Engineer

Grzegorz Glowaty

Grzegorz Glowaty

Software Engineer

Ieva Grublyte

Ieva Grublyte

Software Engineer

Ivan Budiselic

Ivan Budiselic

Software Engineer

Jannis Grönberg

Jannis Grönberg

Software Engineer

Luka Rimanic

Luka Rimanic

Software Engineer

Marina Boia

Marina Boia

Software Engineer

Locations

Zurich, Switzerland

Zurich, Switzerland

Join us in advancing the state-of-the-art in AI and infrastructure