Daniele Grattarola
Staff Research Scientist at Isomorphic Labs
Italy
Summary
🤩
Rockstar🎓
Top SchoolDaniele Grattarola is a Staff Research Scientist based in Italy with 11 years of experience applying geometric deep learning and generative models to problems across structural biology, drug discovery, and clinical neuroscience. Currently at Isomorphic Labs, he has advanced multimodal and post-training approaches for large models after a progression from ML Research Scientist to senior technical leadership roles. His academic background includes a PhD in Computer Science and postdoctoral work at EPFL where he fused neural fields with protein design, and a visiting role at Krembil that produced a clinically-relevant seizure-localization method. An active open-source contributor, he materially improved the popular spektral library—fixing dataset loaders, adding edge-attribute support, and enabling variable-sized inputs—demonstrating a blend of research rigor and engineering craftsmanship. Colleagues rely on him to translate cutting-edge theory into robust, production-ready ML components that impact both labs and industry.
11 years of coding experience
3 years of employment as a software developer
Master's degree Computer Science and Engineering, Master's degree Computer Science and Engineering at Politecnico di MilanoDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at USI Università della Svizzera italiana
Italian, English, Spanish
Stackoverflow
1,517reputation
97kreached
37answers
10questions
deep-learning
top-5%
keras
top-5%
Github Skills (11)
machine-learning10
tensorflow10
graph-neural-network10
python10
deep-learning9
keras9
neural-network6
numpy6
scikit-learn6
linear-regression6
classification6
Programming languages (8)
Github contributions (5)
danielegrattarola/spektral
Jan 2019 - Oct 2022
Graph Neural Networks with Keras and Tensorflow 2.
Role in this project:
Backend Developer & ML Engineer
Backend Developer & ML EngineerContributions:4 releases, 1067 commits, 49 PRs in 3 years 9 months
Contributions summary:Daniele's contributions primarily focused on improving the performance and fixing issues within the GCN model, which includes adding self-loops for GraphSage and making the layers compatible with TF 2.1, particularly with the MinCutPool implementation. They also addressed a significant bug in the TUD dataset loader, ensuring proper functionality. Additionally, the user integrated functionality to support edge attributes and implemented code refactoring, and added support for variable sized inputs, showcasing a commitment to the project's robustness.
pythondeep-learninggraph-deep-learningneural-graphneural-networks
danielegrattarola/keras-multiplexer
Jun 2017 - Nov 2019
Contributions:10 commits, 8 pushes, 1 branch in 2 years 6 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.