Projects
Things I've built
Production systems, research implementations, and open source contributions. Each project is a full case study: problem, architecture, decisions, and results.
ScoutGPT
Agentic AI pipeline over 200M+ row OLAP dataset
Foldex
Multimodal RAG system for document intelligence
ChatMap
Multi-agent geospatial AI system
Cloud2 / OPEA Enterprise-Inference
Enterprise inference infrastructure + open source contributions
Academic Paper Recommendation System
Hybrid NLP retrieval over 99,942 papers — 78.9% accuracy
Deep RL Traffic Control
IEEE TENSYMP 2023 — First Author — Deep RL for intelligent traffic signal control
Deep RL Stock Trading
Springer 2022 — Co-Author — DRL with short selling
Director's Cut
Adaptive film that reshapes itself around your emotions in real time — Gemini 3 NYC Hackathon
FreightMind
NL→SQL logistics analytics + AI invoice extraction with Planner→Executor→Verifier architecture
Texas Property Mapping Interface
Interactive GIS app for Travis County real estate — parcel boundaries, 3D buildings, advanced filtering
AgentBricks
Open-source ML learning platform — build production-grade systems inside a synthetic agent universe
RETROSPEC
Machine-readable AI history knowledge graph — 170+ events, 11 epochs, designed for agents
Heterogeneous Feature Augmentation
Deep hurdle models + CTABGAN for telework prediction — 55% → 75% accuracy
Spatial Microsimulation — Telework Estimates
Census Block Group telework estimates via IPF reweighting across ACS, HPS, and CPS surveys
Commodity Trading with Weather Data
Weather-integrated algorithmic trading strategy for coffee markets — backtested Sep 2023 – Aug 2024
F1 Data Analysis
Telemetry, lap data, and race analytics using the FastF1 Python library
Credit Card Fraud Detection
ML pipeline for fraud detection with WOE feature engineering and SMOTE on 0.17% fraud rate dataset