GitHub

Building systems that remove manual work • LLMs, RAG, Agents • Open to collaboration

💫 About Me

I build AI systems that turn messy docs and repetitive workflows into clean data and automated actions. From payroll parsing at scale to RAG pipelines and inference servers, I ship end-to-end solutions that save time, cut costs, and actually get used.

🎯 What I Do

🧠 Document AI for PDFs/RTFs/Excels (payroll, statements, reports)
🤖 Agentic automation with Browser/Playwright + LLMs
🔎 RAG systems, vector search, re-ranking, and evaluation
🚀 ML deployment with Triton, FastAPI, Docker, GitHub Actions

🏆 Impact Highlights

$20K+

Labor Saved

End-to-end payroll document automation used by real clients

1,000+

Docs Parsed

Robust parsing of PDFs/RTFs → schema-validated JSON

25M+

Rows Analyzed

P&L analytics, EBITDA drivers, and forecasting dashboards

Prod

Deployments

Triton + FastAPI inference services with CI/CD

🌐 Connect With Me

🧠 My Tech Stack

💻 Languages & Frameworks

🤖 AI & ML

🛠 Infra, DevOps & Cloud

🧠 Learning & Exploring

🎯 Featured Projects

Parsed 1,000+ payroll PDFs/RTFs → structured JSON Auto-uploads to Accountant's World; saved $20K+ labor Modular earnings/tax mapping + review UI	Overlays wind hazards with child population exposure Top-5 vulnerability zones + trend time-series Built for UN Hackathon challenge	vLLM + Python backend preprocessors Batch inference (100k images) pipeline Metrics + GitHub Actions CI
Structured JSON outputs with schema validation Amazon vs Walmart scraping + normalization	Public dataset (2006–2025) with dashboards Homicide nowcast + cluster analysis	Upload JSON + LaTeX → export polished PDF Supports per-user storage + versions