I build and investigate security systems across AI security, detection engineering, vulnerability management, cloud security, identity, and security automation.
My background spans cybersecurity analysis, IT infrastructure, software development, and hands-on security labs. I use that combination to build practical security tooling, simulate attacks in controlled environments, engineer detections, and turn security evidence into actionable findings.
- 🔐 Security Engineering — Python security tooling, automation, evidence-driven assessment
- 🤖 AI Security — adversarial testing, prompt injection, jailbreak evaluation, AI red teaming
- 🛡️ Detection Engineering — Wazuh, Microsoft Sentinel, SIEM analytics, endpoint telemetry
- 🎯 Vulnerability Management — vulnerability assessment, prioritization, remediation and validation
- ☁️ Cloud Security — Azure, Microsoft Sentinel and cloud-focused security monitoring
- 🏢 Identity Security — Active Directory, Windows security and privilege management
- ⚔️ Offensive Security — controlled reconnaissance, attack simulation and security testing
AI Red Teaming Lab
Adversarial AI-security training environment covering prompt injection, jailbreak testing, risk classification, scoring and repeatable security evaluation.
AI-RECON
Modular Python security-assessment tooling that collects external evidence, normalizes findings, analyzes exposure and produces console/JSON reports. Built with testing, type checking, packaging and CI validation.
Wazuh Detection Engineering Lab
Endpoint-security lab demonstrating SSH brute-force telemetry, Wazuh detection, investigation and File Integrity Monitoring.
Microsoft Sentinel Detection Engineering Lab
Azure/Microsoft Sentinel lab demonstrating Windows RDP telemetry, enrichment, SIEM ingestion, threat investigation and geographic visualization.
Vulnerability Management with Nessus
End-to-end vulnerability-management workflow covering discovery, authenticated assessment, prioritization, remediation, hardening and verification planning.
Active Directory Security Lab
Windows identity-security environment covering domain-controller deployment, network segmentation, users, organizational units, privilege boundaries and the foundation for controlled AD security testing.
SIEM / Detection: Wazuh · Microsoft Sentinel · Splunk · Elastic · Graylog
Endpoint / IR: Microsoft Defender · SentinelOne · Velociraptor · OPSWAT
Network Security: Wireshark · Suricata · Zeek · Nmap
Vulnerability Management: Nessus · OpenVAS / Greenbone · OWASP ZAP · Nikto
Cloud / DevSecOps: Azure · Docker · GitHub Actions · SonarQube
Security Engineering: Python · Bash · Git · REST APIs · JSON · CI/CD
AI Security: Prompt Injection Testing · Jailbreak Evaluation · AI Red Teaming · LLM Security Evaluation
I care about more than running security tools. My projects emphasize:
Security Problem
↓
Controlled Test / Evidence
↓
Detection or Analysis
↓
Structured Findings
↓
Remediation / Hardening
↓
Validation
Where possible, I document what was tested, what evidence was observed, what the result means, and how the control can be improved.
I'm currently deepening my work in:
- AI security and adversarial testing
- Detection engineering
- Security automation with Python
- Cloud security
- Vulnerability and exposure management
- Security engineering for modern AI-enabled systems
Build it. Break it. Detect it. Fix it. Validate it.
