Postdoctoral Fellow at Indiana University Bloomington
Baltimore, Maryland, United States
Join Prog.AI to see contacts
Join Prog.AI to see contacts
Summary
👤
Senior
🎓
Top School
Parichit Sharma is a PhD candidate at Indiana University Bloomington focused on unsupervised ML, data-centric AI, and bioinformatics, with a track record of turning research into scalable, open-source software. He has delivered substantial performance gains in large-scale clustering and genomics pipelines, including a data-centric approach that achieved 5–220x speedups on clustering and reduced training time by about 66% while preserving accuracy, plus a scalable 10M+ point K-means clustering under four minutes. His work has been published at ICML, NeurIPS, and IEEE DSAA, and he actively contributes to open-source projects such as DIPY, where he improved the workflow system and CLI usability. He embodies an open science ethos, having created software and web portals downloaded over 30,000 times. His experience spans academia and industry, with credentials including Google Summer of Code and roles at Ancestry and Diffusion Imaging in Python, underscoring a practical, production-oriented mindset. Based in Bloomington, he seeks to apply data-centric AI to biology and healthcare, delivering trustworthy and efficient AI solutions.
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:
Back-end Developer
Contributions:65 commits, 23 PRs, 64 comments in 3 months
Contributions summary:Parichit primarily contributed to enhancing the DIPY workflow system, a library for medical imaging in Python. They focused on improving the robustness and usability of the workflow framework, including adding argument checks, refining help messages, and fixing formatting. Their work involved modifying core workflow components, specifically within the `dipy.workflows` module, demonstrating a focus on functionality and maintainability of the library's command-line interface.
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.