Mara Graziani
Research Scientist at IBM Research
Sierre, Wallis, Switzerland
Summary
👤
Senior🎓
Top SchoolMara Graziani is a research scientist at IBM Research Europe with nine years of experience applying multimodal foundation models to accelerate scientific discovery. She earned a PhD from the University of Geneva for work on interpretable deep learning and spent part of her doctorate at Harvard Medical School exploring clinician–AI interaction, bridging technical advances with real-world clinical workflows. Before her PhD she completed an MPhil in Machine Learning, Speech and Language at Cambridge and began as an ICT engineer focusing on EMG-driven prosthetics, giving her a rare mix of biomedical signal processing and foundation-model expertise. Her recent work blends multimodal representation learning with interpretability, aimed at making large models both powerful and actionable for scientists. Multilingual and based in Switzerland, she combines rigorous academic training with hands-on research collaborations across IBM and Swiss universities.
9 years of coding experience
6 years of employment as a software developer
Master of Philosophy (M.Phil.) Machine Learning Speech and Language Technology, Master of Philosophy (M.Phil.) Machine Learning Speech and Language Technology at University of CambridgeDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of GenevaMaster of Science (MSc) student in Artificial Intelligence and Robotics, Master of Science (MSc) student in Artificial Intelligence and Robotics at Sapienza Università di Roma
Italian, English, Spanish, French
Github Skills (22)
relevance10
bidirectional9
histopathology9
regression8
use-case8
cancer-detection8
classification7
multiclass-classification7
git6
neuroimaging5
image-segmentation5
tsne5
machine-learning5
github-enterprise5
deep-learning4
Programming languages (3)
Github contributions (5)
maragraziani/miccaihackathon_shifts
Aug 2022 - Sep 2022
Contributions:41 commits, 40 pushes, 1 branch in 7 days
medgift/iMIMIC-RCVs
Jul 2018 - Sep 2018
This repository contains the code for implementing Bidirectional Relevance scores for Digital Histopathology, which was used for the results in the iMIMIC workshop paper: Regression Concept Vectors for Bidirectional Explanations in Histopathology
Contributions:46 commits, 2 PRs, 51 pushes in 1 month
regressionworkshopexplanationsvectorsscores
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.