Experience
PricewaterhouseCoopers
- Engineered a full-stack AI platform using Streamlit and FASTAPI, integrated with Azure Form Recognizer, reducing document processing time from 10 hours to 2 minutes, achieving 99% extraction accuracy across 10,000+ financial records.
- Boosted model precision by 20% through the implementation of demographic profiling and NLP, enhancing classification accuracy in automated tax form analysis.
- Developed a Python-based chatbot for a national nonprofit within 3 weeks, increasing user engagement by 70% for 1,200 students.
- Visualized tax advisory performance trends using Tableau and Plotly, delivering dynamic dashboards that streamlined decision-making for senior stakeholders and improved service quality metrics by 35%.
Jules Stein Eye Institute
- Published 7 papers in Ophthalmology and American Glaucoma Society journals, applying AI models to 3,000+ patient records to improve glaucoma progression forecasting.
- Built deep learning models in Python and R to predict visual field degradation, increasing early detection accuracy by 28%.
- Performed survival analysis and multivariate regression to estimate progression rates, uncovering 5 key prognostic factors used to tailor personalized care plans.
American Express
- Directed a team of 3 engineers to develop an ML pipeline processing 10.4M+ financial records, increasing classification accuracy by 30% and enhancing fraud detection precision.
- Analyzed campaign performance data using Pandas and Scikit-learn, optimizing resource targeting strategies and improving ROI by 80% across multiple campaigns.
- Deployed ensemble models in Jupyter Notebook to identify high-probability customer segments, increasing lead conversion by 3x.
- Automated reporting workflows, reducing model iteration cycle time by 50% and enabling faster stakeholder decision-making.