Karan Bhanot is a Senior Data Scientist with a PhD in Computer Science and a decade of experience applying machine learning and deep learning to healthcare and real-world data. He combines rigorous research—10+ publications and multiple first-author papers on synthetic data, fairness, and responsible AI—with hands-on engineering, having led end-to-end ML systems and an 81-scenario fairness auditor that cut evaluation time substantially. At Norstella he works with open-source LLMs and prompt engineering to convert unstructured clinical notes into structured data, while previously securing and managing multi-year research grants with IBM. Karan’s background spans full-stack implementation (including a public ML-React-Flask app template) to training generative models on 300k EHR records, reflecting both product and research fluency. He has a track record of mentoring and leading large student teams and reducing engineering friction through better tooling and code practices. Based in Bethesda, MD, he brings a rare mix of academic depth, reproducible research, and pragmatic product delivery in ML for healthcare.
10 years of coding experience
6 years of employment as a software developer
Classes 11th and 12th (High school equivalent), Non-Medical (Engineering and related fields), Classes 11th and 12th (High school equivalent), Non-Medical (Engineering and related fields) at Stepping Stones Sr. Sec. School
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Rensselaer Polytechnic Institute
Bachelor of Technology - BTech, Computer Science and Engineering, Bachelor of Technology - BTech, Computer Science and Engineering at Punjab Engineering College
This is a template for creating a Machine Learning application with its front-end developed using React which interacts with a Flask service as the back-end and makes predictions.
Role in this project:
Full-stack Developer
Contributions:25 commits, 18 PRs, 18 pushes in 1 month
Contributions summary:Karan primarily worked on developing the front-end of the machine learning application template using React. They started by creating the initial React application structure and then implemented UI components using React Bootstrap. The user also integrated a basic form and incorporated a prediction feature with a connection to a mock API endpoint. Furthermore, they updated the UI to connect with a Flask backend, incorporating form data submissions and displaying prediction results.
This Python project develops a LDA model which trains on various Wikipedia articles based on a keyword and then suggests Wikipedia articles based on a search query.
Contributions:19 commits, 1 PR, 14 pushes in 7 months
querypythontrainsldalda-model
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.