I architect data pipelines and the analytics layer on top of them — the end-to-end work that's increasingly recognized as analytics engineering, sitting at the gap between roles that have traditionally been separate. 10+ years across healthcare and public health, from extraction to insight delivery.

Live flight tracking platform with OAuth2 authentication, custom ETL pipeline, and interactive dashboards tracking 5,000+ aircraft in real-time.

Tech: Python • Dash • Plotly • Pandas • OAuth2 • Gunicorn • Render

Urban mobility intelligence platform with Protocol Buffer binary data handling, event-driven architecture, and geospatial analysis using DuckDB.

Tech: Python • DuckDB • Protocol Buffers • GTFS • Event-Driven Architecture

Production data engineering pipeline with Airflow orchestration, Docker containerization, and Parquet optimization for drug safety monitoring.

Tech: Python • Airflow • Docker • Postgres • Parquet • Streamlit

Marathon training assistant using Retrieval-Augmented Generation with LangChain, ChromaDB vector search, and semantic embeddings.

Tech: Python • LangChain • ChromaDB • RAG • Vector Database • Streamlit

AI-powered healthcare information retrieval system with Groq/Llama integration, vector search, and safety guardrails.

Tech: Python • Groq • Llama • ChromaDB • RAG • Healthcare AI

Privacy-first AI symptom analysis application with Groq/Llama3-70B integration, built with TypeScript and React.

Tech: TypeScript • React • Groq • Llama3-70B • LocalStorage • Vercel

Machine learning analysis of U.S. state health outcomes using Random Forest, PCA, and K-means clustering on 2025 data.

Tech: Python • Scikit-learn • Random Forest • PCA • K-means • R Shiny • Streamlit

Causal inference analysis proving poverty causes diabetes using CDC Health Rankings data and statistical modeling.

Tech: Python • Causal Inference • Statistical Modeling • Public Health Data

Statistical modeling of U.S. health outcome disparities using 2025 Health Foundation data.

Tech: Python • Pandas • Statistical Analysis • Public Health Analytics

Analytics Engineering: End-to-End Pipeline Design • Insight Delivery • Self-Service Analytics • EHR Data Integration

Data Engineering: ETL Pipeline Design • Real-Time Data Processing • Event-Driven Architecture • Data Quality Frameworks

ML & AI: Statistical Modeling • Machine Learning • Causal Inference • Predictive Analytics • RAG Systems

Technologies: Python • R • SQL • TypeScript • Docker • Airflow • Postgres • DuckDB • LangChain • ChromaDB

Domains: Healthcare Analytics • Public Health • Geospatial Analysis • Real-Time Monitoring