RootReap3r.

AI Red-Teamer / AI Security Engineer (Contract)

• Exploited 100+ direct and cross-domain prompt-injection/jailbreak vulnerabilities across client LLM-integrated products within the first week, validated and scored via structured red-team taxonomy.
• Built and deployed a multi-tenant AI chat widget embeddable on any site in <30 min, with production-grade security: CORS allowlisting, prompt-injection screening, XSS-safe rendering, CSRF protection, timing-safe auth.
• Surfaced MCP tool-poisoning, schema injection, and cross-server privilege escalation via over-privileged server exploitation across client AI tool infrastructure.

Senior Cybersecurity Engineer

• Zero-Day Discovery & Detection Engineering: Drove security accreditation for a $147B TS/SAP cloud program by manually reverse-engineering zero-days missed by enterprise tooling, building an AI correlation engine (NVD/CVE/CNNVD) to automate triage, and engineering Splunk detections that cut C2 dwell-time from hours to <2 minutes—securing full ATO across 10 NIST Rev 5 control packages.
• Supply-Chain Security: Built a supply-chain risk correlation tool cross-referencing NVD and ExploitDB against asset versions to surface unpatched vulnerabilities, with open-source/GitHub sweeps and foreign-influence/vendor-provenance checks on hardware, software, and AI components.
• Threat & Risk Assessments: Ran 2,730 adversary-informed threat and risk assessments across unclassified/Secret/TS-SAP environments, correlating 524 vulnerability scans and 476 audits through offensive security expertise and exploit research.
• Incident Response & Scenarios: Architected the incident response plan and designed 16 quarterly adversarial scenarios spanning four classification environments (unclassified through TS/SAP), authoring each from threat scenario through after-action report.
• Compliance & Governance: Authored risk and controls accreditation packages (~2,500 controls, SCTMs, SSPs) as Lead ISSO for Sentinel and Nuclear Command & Control programs.

Security Program Manager

• Personnel & Insider Threat: Directed personnel security and insider threat program for 2,350+ AFNWC personnel holding Top Secret/SAP access—vetting for counterintelligence exposure, adjudicating clearance eligibility, and validating need-to-know before granting access to Restricted Data.
• Physical & Nuclear C2 Security: Owned industrial/physical security for $41M+ in SAP/TEMPEST facilities across multiple classified vaults and secured networks transmitting Nuclear Command & Control design data and DOE Restricted Data, running adversarial assessments across all control layers to close every gap identified and maintaining zero attributable incidents.
• Customer Recognition (2021): Received formal recognition following an ICBM Systems Directorate Security Support PMR after the government customer specifically cited outstanding performance and the development of an innovative new badging-system plan provided to the Deputy Director.

Cyber Automation Lead

• Built SOAR/PowerShell-Python automation for account remediation, access provisioning, and IR triage—cutting escalation decision time on leakage/compromise cases from minutes to seconds—across DISA, White House, Pentagon, and 7th Fleet.

Cyber Investigations Lead

• Led response to the 2019 credential-stuffing campaign compromising 900+ accounts, correlating device/IP/geolocation/VPN signals to restore 100% of accounts to original owners.

Incident Response Lead

• Advanced from help desk analyst to IR Lead, resolving 10,264 tickets and coordinating a multi-person IR team while sustaining a 96% stakeholder satisfaction scorecard.

Teal Rope Initial Training

Completed Teal Rope Initial Training through the 81st Training Wing Sexual Assault Prevention and Response Office.

Weapons Director

A Weapons Director sits in an Air Operations Center or Control and Reporting Center, watching a live radar picture and directing fighter aircraft in real time — sorting real threats from noise, prioritizing which contact gets worked first, and issuing short, unambiguous instructions to pilots who are relying on your read of the situation because they can't see what you can see. It's high-tempo decision-making under incomplete information, inside a strict rules-of-engagement framework, where a wrong call has immediate consequences and there's no time to second-guess.

That's a closer match to AI red-teaming and incident-response work than it might sound: triaging a flood of findings in real time, deciding what's a real threat versus noise, working inside an explicit scope/rules-of-engagement boundary, and communicating clearly and fast when the picture is incomplete. The instincts built directing intercepts translate almost directly to directing a red-team engagement or running point during a live incident.

M.S. Artificial Intelligence · Georgia Institute of Technology

In progress (part-time). Research: adversarial robustness & red-teaming of LLMs and agentic systems.

B.A.S. Cyber Operations, Defense & Forensics · University of Arizona

NSA Center of Academic Excellence in Cyber Operations; malware reverse engineering, digital forensics.

AFNWC Security Community Award · Air Force Nuclear Weapons Center

Security Outstanding Team Award, NXOS Security Team. Also: Minuteman III Personnel Award, ICBM Personnel Award.

AI-Powered Active Defense & Threat-Hunting Platform

Multi-agent active-defense platform using ML-based C2 beacon detection, passive attribution (geolocation, JA3, threat-intel), confidence-gated response, and cryptographic chain-of-custody evidence; shipped 105 passing tests and one-command FBI/CISA report generation (STIX 2.1, IOC).

LLM Safety-Evaluation Harness

Red-team harness replacing self-graded LLM safety scoring with deterministic pass/fail gates (canary extraction, PII regex, injection detection) and an advisory-only LLM judge calibrated against a golden set, aligned to NIST AI RMF MEASURE/MANAGE, with a code-enforced allowlist immune to prompt-injection scope escape. Read the technical breakdown →

AI-Driven NIST 800-53 Rev 4→5 Migration Pipeline

Pipeline generating SCTM, eMASS export, and POA&M items from SSP content, grounding every AI judgment against the full 1,189-entry NIST Rev 5 catalog; provider-agnostic (Anthropic/OpenAI/Bedrock GovCloud), deployable air-gapped/NIPR with zero code changes.

Adversarial LLM Incident-Response Tabletop Engine

Self-contained engine where an LLM plays a state-consistent threat actor across 23 scenarios and 9 MITRE-mapped APT profiles, with attacker/grader roles split across separate API passes and offline .docx after-action reports.

From Cryptic Commands to Agentic CLI: How Claude Code Rewired the Terminal

Why decades of memorized flags and manual scripting are giving way to natural-language, autonomous terminal work — with a side-by-side comparison of manually diagnosing a broken service versus letting Claude Code do it end-to-end.

From Tool Mastery to Agent Orchestration: How AI Rewired Offensive Cybersecurity

How agentic AI reshaped offensive security between 2016 and 2026 — RoE-gated agent orchestration, hyper-scale recon, exploitation chaining, the global AI tooling landscape, and the AI-vs-AI attack surface: indirect prompt injection, context poisoning, and agent hijacking.

My First Week Red Teaming as a Contractor: What Nobody Tells You

Field notes on an unexpectedly diverse team, exploiting 100+ vulnerabilities in a week, and a recognition gap around obfuscated prompt injection — with two rewritten examples showing a real finding versus one that isn't.

Building recon-sweep: A Scope-Gated Harness for Agentic AI Red Teaming

Inside recon-sweep's architecture — code-level scope-gated pentesting and falsifiable, canary/PII/injection-gated AI evaluation instead of LLM self-grading.

Before ChatGPT: The First AI Jailbreak Community Nobody Talks About

A firsthand account of adversarial prompting against Midjourney's content filter months before ChatGPT's "DAN" prompts — and why keyword/semantic-matching guardrails still fail the same way today.