Shreyas Fadnavis
AI Lead at Bioscope AI
Boston, Massachusetts, United States
Summary
👤
Senior🎓
Top SchoolShreyas Fadnavis is an AI lead with a decade of experience at the intersection of optimization, machine learning, and applied mathematics, currently leading AI at Bioscope AI in Boston. He combines deep academic rigor—PhD in Intelligent Systems Engineering and postdoctoral work at Harvard and J&J—with hands-on engineering in medical imaging and computer vision. His open-source contributions to the widely used DIPY library include implementing advanced diffusion MRI models (MSMT-CSD and IVIM) and improving model fitting and denoising pipelines. He has steered teams in industry as a principal AI engineer and built multi-view learning and model-fitting algorithms during research stints at IBM and Google GSoC. Shreyas pairs a product-aware mindset (product management coursework at Kellogg) with a proven track record of translating complex computational imaging research into production-ready solutions. Colleagues describe him as someone who bridges theory and practice, often spotting numerical or modeling improvements others miss.
10 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD, Intelligent Systems Engineering, Neuroengineering, Machine Learning, Doctor of Philosophy - PhD, Intelligent Systems Engineering, Neuroengineering, Machine Learning at Indiana University BloomingtonBachelor of Engineering - BE, Computer Science, 9 / 10, Bachelor of Engineering - BE, Computer Science, 9 / 10 at Pune Institute of Computer TechnologySSC, Junior High/Intermediate/Middle School Education and Teaching, SSC, Junior High/Intermediate/Middle School Education and Teaching at Loyola High School & Junior College PuneHigher Secondary Certificate, Bifocal, Computer Science (HSC), Higher Secondary Certificate, Bifocal, Computer Science (HSC) at Fergusson CollegePostdoctoral Fellow, Multimodal Machine Learning and Computational Imaging, Postdoctoral Fellow, Multimodal Machine Learning and Computational Imaging at Harvard UniversityKellogg School of Management
English, Marathi, Hindi
Stackoverflow
73reputation
2kreached
5answers
1question
Github Skills (16)
cvxpy10
scipy10
diffusion-mri10
python10
scientific-computing10
numpy10
machine-learning8
data-analysis8
neuroimaging8
regression6
pandas6
pca6
precision-recall6
training-data6
classification6
Programming languages (10)
Github contributions (5)
dipy/dipy
Mar 2018 - Nov 2022
DIPY is the paragon 3D/4D+ medical imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.
Role in this project:
Data Scientist
Data ScientistContributions:25 reviews, 234 commits, 54 PRs in 4 years 8 months
Contributions summary:Shreyas primarily contributed to the development and testing of a multi-shell constrained spherical deconvolution (MSMT-CSD) model, focusing on the implementation of an IVIM model for multi-shell data denoising and analysis. They made several modifications to the existing MSMT-CSD code by including features like the segmentation using Hidden Markov Random Fields (HMRF) classifier, calculating the mean diffusivity and fractional anisotropy based on the DTI model, and integrating the new IVIM model to improve the model fitting for the diffusion data. The user updated the example code and fixed various issues.
signalpythonmicrostructurespatialtractography
ShreyasFadnavis/Practice
Apr 2018 - Dec 2024
Contributions:13 pushes in 6 years 9 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.