What I optimize for
Clear failure states, evidence a reviewer can inspect, and operational outcomes that survive beyond a demo.
About
I care about the space between a promising model and a system people can trust.
That means explicit contracts, evaluation sets, reviewer fallbacks, observable traces, and deployment boundaries that match the data.
Across more than seven years, my work has moved from biomedical informatics and clinical-data foundations to healthcare analytics products, payer AI modernization, local document intelligence, and agentic insurance workflows.
How I lead
I translate ambiguous workflow problems into contracts, evaluation plans, release gates, and shared language across engineering and operations.
What stays private
Employer data, production rules, private model routes, confidential screenshots, credentials, PHI, PII, and proprietary APIs.
Education
- M.S., Biomedical Informatics — University of Chicago, 2019
- Summer School, Public Health Modeling — Yale University, 2019
- B.Tech., Computer Science & Engineering — SRM University, 2018
Credentials
- AWS Certified Machine Learning Engineer — Associate
- Microsoft Azure AI Fundamentals (AI-900)
- Microsoft Power BI Data Analyst (PL-300)
Outside the primary lane
Forecasting, quant systems, sports models, and research tooling.
These interests sharpen how I think about calibration, backtests, uncertainty, and experiment design. They live in the Lab so the primary healthcare and insurance story stays clear.
Explore the LabGet in touch