Projects / Selected work
These projects show how I approach the full system: useful models, safeguards, production operations, and results that people can inspect and trust.
Agentic AI / Security research
I built a read-only AI agent that researches one domain, shows its sources, and explains how it reached a verdict.
Production ML / DNS security
A production machine-learning system that screens live DNS traffic and flags malicious or look-alike phishing domains in near real time. A four-model ensemble over 50+ engineered domain features is backed by a multi-stage verification safety net that confirms threats and suppresses false positives before they block a real customer. It flags roughly 800 malicious domains a day at about 90% precision. Built at ThreatSTOP.
A quick scan
The recruiter overview connects these projects to my wider experience in production AI, enterprise learning, knowledge systems, and cybersecurity.
RAG-based LLM agent