I'm a Master's student in Applied Data Science at the University of Chicago and a Computer Science and Computational Modeling and Data Analytics graduate from Virginia Tech. I enjoy building data-driven systems and scalable applications that bridge software engineering, analytics, and cloud technologies.
Across academic, research, and internship experiences, I have worked on data pipelines, automation workflows, and full-stack applications. I focus on writing clean, reliable code and turning raw data into structured, usable insights that support real-world decisions.
📫 Actively seeking Full time roles after graduating in Data Science, Data Engineering, or Cloud Architecture — View my resume
-
🏙️ Oasis – Small Business Survival Intelligence:
ML-powered platform predicting small business closure risk using XGBoost + SHAP explainability on Chicago open data. Features a 3D Mapbox dashboard, multilingual AI consultant (Gemini + Groq fallback), and voice-enabled insights with PDF reporting. Built with FastAPI, React, and deployed via Docker on DigitalOcean. WildHacks project. -
🧠 Anchor – AI Focus Companion:
Real-time AI system that detects task drift using window activity + webcam signals, and delivers personalized interventions via an intelligent agent. Built with FastAPI, React, WebSockets, and multi-model reasoning (Markov chains + LLMs). Yale Hackathon Project. -
🏥 Clinical KG Extraction – UChicago AI+Science Hackathon:
Multi-agent pipeline extracting clinical knowledge graphs from doctor-patient transcripts. Built a 5-stage architecture (chunker, dual extractor, schema enforcer, critic, refiner) scoring 0.848 composite on 20 patients and 0.857 on unseen holdout data. Added Whisper-based audio timestamp tagging linking every KG node to the exact moment it was mentioned in the recording. -
🔬 Cell Nuclei Segmentation:
Instance segmentation of cell nuclei in microscopy images using the pre-trained Cellpose model. Evaluated performance on 50 paired images with metrics (Precision, Recall, F1, Dice) and visual overlays. -
🏥 ER Wait Time Forecasting:
Time series forecasting model for EMS dispatch wait times using XGBoost and NYC Open Data. Focused on healthcare analytics and model explainability. -
✈️ Airport Delay Forecasting:
Time series forecasting of U.S. flight delays using SARIMA models, STL decomposition, and feature engineering on 26M+ flight records to analyze airport congestion dynamics. -
🚗 Crash Rate Prediction:
Full-stack web app to predict crash rates using TensorFlow, FastAPI, and React. -
🕊️ AI Web Scraper for Parish Data:
ETL + LLM-powered scraper with Power BI dashboards for Catholic Leadership Institute. -
🌍 Landslide Prediction:
Tree-based classification model to predict landslide-prone regions using NASA GLC data.
Languages: Python, Java, R, SQL, JavaScript, C, MATLAB, HTML/CSS
Frameworks & Tools: TensorFlow, FastAPI, React, XGBoost, BeautifulSoup, Power BI, Docker, Git
Cloud & MLOps: AWS (S3, ECS, SageMaker, Lambda), Azure, GitHub Actions, REST APIs
- Cloud-native deployments for ML systems (Docker + AWS)
- Retrieval-Augmented Generation (RAG) pipelines with LLMs
Thanks for stopping by! 🚀