Professional Summary
Cybersecurity MSc graduate (Oklahoma City University, GPA 3.7) with 1.5+ years of active AI evaluation and safety contract work across multiple frontier-LLM platforms, alongside a hands-on background in SOC-style threat detection, vulnerability management, and M365 security administration. Maintains a public AI Evaluation & Safety portfolio on GitHub. Holds Cisco CyberOps Associate, SC-900, AWS Cloud Practitioner, and Microsoft 365/Azure/AI fundamentals; currently pursuing BTL1 (Blue Team Labs One) for hands-on defensive practice. U.S. Green Card holder, eligible for Secret clearance.
Core Skills & Tools
- AI / ML Security
- AI red teaming, LLM security testing, adversarial prompt design, AI agent evaluation, AI safety evaluation, reward hacking detection, OWASP Top 10 for LLM Applications
- Security Operations
- Threat detection, incident response, vulnerability assessment, SIEM (Splunk, Microsoft Defender), MISP threat intelligence, OWASP Top 10
- Cloud & Identity
- Microsoft Azure AD, AWS Cloud Practitioner, Microsoft Intune, MFA, conditional access, M365 security administration
- GRC & Compliance
- NIST, ISO 27001, HIPAA, risk assessment, policy documentation, access controls
- Tools
- Nessus, Nmap, Wireshark, Splunk, Microsoft Defender, MISP, Docker, GitHub, Streamlit
- Automation & Scripting
- Python, PowerShell, Bash
- Systems & Networking
- Windows, Linux, Active Directory, networking fundamentals, VPN
Professional Experience
AI Evaluation & Safety Specialist
2024 – Present- Active across multiple frontier-LLM evaluation and safety platforms — including Snorkel AI, Alignerr, Mercor, Meridian (Invisible), RemoteXperts, and LinkedIn's expert verification program — covering AI red-teaming, prompt-injection assessment, AI agent evaluation (reward-hacking detection, evaluator-manipulation prevention), data annotation, and rubric design.
- Collaborated with AI research teams to evaluate and harden LLM security and safety; designed adversarial test cases targeting prompt injection, jailbreak, and behavioral manipulation; documented findings in NDA-compliant evaluation reports used to inform safety guardrails.
- Conduct quality-assurance audits of autonomous AI agent scenarios used in frontier LLM training: review YAML task specifications and rubrics, audit PASS/FAIL trajectories to verify legitimate task completion vs. reward hacking, and analyze execution logs for world-agent response consistency.
- Maintain a public AI Evaluation & Safety Portfolio (NDA-compliant) on GitHub for professional peer review.
- Apply OWASP Top 10 for LLM Applications, the OWASP Agentic AI Top 10, and NIST AI RMF references to evaluate model and agent behavior across multiple frontier model families.
Cybersecurity Intern – Corporate Information Systems
May 2024 – Aug 2024- Embedded with the corporate Network Security team on live threat-intelligence and security-operations initiatives.
- Built and documented a secure Docker environment for the MISP malware-information-sharing platform, enabling the team to ingest and operationalize threat indicators.
- Developed Python scripts to support security tool integration and data handling; participated in vulnerability scanning (Nessus) and secure architecture reviews.
- Presented project outcomes to senior IT staff and authored internal process documentation.
Technical Support Specialist – Microsoft Windows & Office 365
Jan 2021 – Sep 2024- Provided enterprise-level technical support for Microsoft customers globally, building deep endpoint security and identity-management expertise across Microsoft 365 services.
- Resolved Tier-2 issues spanning identity access, password resets, MFA setup, and conditional-access policies; configured Active Directory permissions and assisted with Intune deployment and patch enforcement.
- Automated recurring support workflows in PowerShell, reducing manual ticket-handling time and improving first-response SLAs.
- Coordinated with internal security teams to maintain endpoint compliance and system hardening.
Student Library Assistant (Research & Information Support)
Sep 2023 – Apr 2025- Provided research and information-support services to students and faculty in a university library environment.
- Resolved patron-facing identity/access issues across Microsoft 365 services (Teams, SharePoint, Exchange, OneDrive).
- Documented common workflows to streamline future support and student onboarding.
IT Support & Systems Administrator
2014 – Jan 2021- Provided Tier 1–2 IT support in a multi-user environment; managed helpdesk tickets and resolved endpoint, network, and access issues.
- Implemented basic security protocols, managed user access, and advised on procurement of secure IT equipment.
Education
- M.Sc. Cybersecurity — Oklahoma City University ·
- IT Support Graduate — Per Scholas ·
- Junior Cloud Practitioner — ChooseU ·
Training & Continuing Education
-
Cybersecurity Mentorship Program — Defensive Security Track — Cybersecurity Clarity ·
Structured mentorship in defensive security fundamentals, ethical hacking, OWASP Top 10, and CTF-style lab scenarios. Capstone: automated OWASP Top 10 vulnerability tests in Python.
Certifications
- Microsoft SC-900 — Security, Compliance & Identity Fundamentals
- AWS Certified Cloud Practitioner
- Google Cybersecurity Certificate
- Microsoft 365 Fundamentals (MS-900)
- Microsoft Azure Fundamentals (AZ-900)
- Microsoft AI Fundamentals (AI-900)
- CCEP — Certified Cybersecurity Educator Professional (Red Team Leaders)
- CTIGA — Certified Threat Intelligence & Governance Analyst (Red Team Leaders)
- AI Security — Securiti AI
- Cisco CyberOps Associate
- BTL1 (Blue Team Labs One)
Projects & Labs
- Adverse Insight — Streamlit + OpenAI app chaining three AI agents to extract clauses from contracts, red-team-score them for hidden risk, and auto-draft negotiation scripts. Built in 48 hours. [GitHub]
- AI Evaluation & Safety Portfolio (NDA-Compliant) — Public GitHub portfolio of selected AI red-teaming, evaluation, and safety workflows for peer review.
- CodePath Applied AI Engineering Program — Admitted; focus on threat detection, security automation, and identifying vulnerabilities in AI-driven systems.
- Hands-On Labs & Competitions — National Cyber League (NCL) 2023: log analysis, packet inspection, cryptography. TryHackMe & Hack The Box: SOC Level 1, Pre-Security, and Junior Penetration Tester paths completed. MSc Capstone: identified and remediated network vulnerabilities using Nessus and Nmap. Home Lab: Active Directory simulation with Windows Server, Ubuntu VMs, and M365 configuration.