A selection of things I've built — AI pipelines, security tooling, DevOps platforms and more.
Comprehensive network security analysis tool that processes PCAP files and live traffic to detect 8+ threat types through hybrid detection combining rule-based Sigma analysis, behavioral anomaly detection, and Random Forest ML classification.
Autonomous LAN security monitoring system built with Go, Nmap, and MikroTik RouterOS. Automatically discovers devices, scans them at configurable depth, and generates scheduled HTML security reports — all running as a single stateless binary inside a minimal Docker container.
Distributed intelligence platform transforming optical sensors into defense-grade threat detection nodes for airspace security. Addresses modern unmanned aerial threats with <1s detection latency, 24/7 operation, and $50+ per-device deployment costs.
Fully containerized enterprise-network simulation with 7 security zones, 6 firewalls, IPSec IKEv2 site-to-site VPN, Suricata IDS, SIEM, EDR, and Tenable Nessus — entirely declared as code with Docker Compose and validated by 20+ automated E2E tests.
Tabular Q-learning agent solving the classic MountainCar-v0 control problem. The car learns to build momentum by rocking back and forth to reach the goal — a counter-intuitive strategy discovered autonomously through the Bellman equation and epsilon-greedy exploration.
Fully automated vulnerability scanner wrapper for OpenVAS/GVM with zero-config subnet detection, idempotent scan targets, PDF reporting, and SMTP delivery — designed to run unattended via cron for continuous security monitoring.
Academic research project demonstrating sophisticated malware techniques including adaptive attack strategies, multi-protocol lateral movement, and self-replication in controlled lab environments.