cortney/bowman
Available·Charlotte Metro · Remote

CortneyBowman.

~/AI Engineer·RAG Architect·Edge AI Builder·Security-First Developer

Building production-grade AI systems at the intersection of edge inference, LLMs, and security. U.S. Air Force veteran turned engineer, currently a Security & Awareness Analyst at Centene.

See the work→Get in touchLinkedIn ↗
10+
Years in security & systems
4.0
Graduate GPA
~100ms
Edge AI inference
3+
Production AI surfaces shipped
Scroll
OpenAI
Anthropic
Llama 3.2
RAG
Chroma
FAISS
YOLOv8
Hailo-8 NPU
GStreamer
AWS
Python
React
TypeScript
MITRE ATT&CK
Zero Trust
MLOps
OpenAI
Anthropic
Llama 3.2
RAG
Chroma
FAISS
YOLOv8
Hailo-8 NPU
GStreamer
AWS
Python
React
TypeScript
MITRE ATT&CK
Zero Trust
MLOps
01 / About

I bridge worlds: security, systems, and AI.

I design and ship AI systems that run in production. Edge inference on custom hardware, LLM-powered analytics, distributed architectures over local networks, and the observability layer that makes them trustworthy. I build with the OpenAI and Anthropic APIs, run Llama 3.2 locally, and care about the engineering judgment that separates a demo from a system: latency, false-positive tuning, safety, and architecture that holds up under real load. I work fluently with AI tooling — Cursor, Copilot, local LLMs — as a collaborator, not a crutch.

My foundation is unusual on purpose: U.S. Air Force Security Forces veteran, B.S. in Computer Science, M.S. in MIS with an Information Security specialization (4.0 GPA), Microsoft-certified Power BI Data Analyst (PL-300), Microsoft Power Platform Fundamentals (PL-900), AWS Cloud Practitioner, Google Cybersecurity certified, and 5+ years of hands-on threat analysis. That security-first instinct shapes every system I ship.

OpenAI APIAnthropic APIRAGEdge AIMLOpsAWSPythonReact
Demo → Production

Latency budgets, observability, graceful degradation. AI systems that survive contact with real users.

Security-Native

Threat-modeling, prompt injection, adversarial ML, zero-trust thinking baked in from day one.

Edge-First Instinct

On-device inference. Zero cloud dependency when the workload doesn't need it. Your data stays with you.

Military Discipline

Five years in Air Force Security Forces — mission-critical execution under pressure. It carried over.

02 / Journey

From the flight line to the frontier.

Air Force veteran with five years in cybersecurity — now building AI with an adversary in mind. Every role compounds — military discipline, large-scale data systems, enterprise security, and now applied AI.

  1. Jan 2025 - Present
    Remote · Charlotte Metro
    Current

    Security & Awareness Analyst

    Centene Corporation
    • Sole data analyst spearheading analytics across the security awareness team. Translate raw security telemetry into Power BI and Power Automate dashboards that surface engagement, compliance, and behavioral-risk metrics for leadership across a workforce of 80,000+.
    • Co-execute monthly phishing simulation campaigns targeting 80,000+ employees enterprise-wide (KnowBe4). Own campaign telemetry, click-rate analysis, repeat-offender identification, and post-campaign reporting that measurably reduces organizational risk.
    • Integrate LLM tooling (Microsoft Copilot, Copilot Studio, OpenAI) into security workflows using prompt engineering and structured output extraction to drive compliance insights and analyst efficiency.
    • Bridge cybersecurity principles with AI development practices. Apply zero-trust thinking and an adversarial mindset to model behavior, prompt injection risks, and responsible AI deployment patterns.
  2. Jan 2025 - Present
    Self-directed
    Building

    AI Engineer

    Independent Projects
    • Architected and deployed FameAILab, a fully local edge AI security platform. Reolink PoE camera, Raspberry Pi 5, Hailo-8 NPU running YOLOv8s at 25fps with ~100ms inference. GStreamer pipeline, SQLite logging, Flask REST API (9 endpoints), Telegram alerts, systemd services.
    • Built distributed two-Pi architecture over LAN. Inference node serves a detection API consumed by a separate Ollama (Llama 3.2) and SOC dashboard node. Zero cloud dependency, zero exfiltration.
    • Engineered false-positive tuning v2: 3-of-5 frame persistence buffer, dynamic confidence thresholds, alert cooldown logic, and ROI masking infrastructure. Moved the system from prototype noise to production-grade signal.
    • Developing RAG pipelines (Chroma, FAISS), agentic workflows (OpenAI Agents SDK, CrewAI, LangGraph), and AI-native React dashboards for security operations.
  3. Dec 2023 - Dec 2024
    Charlotte, NC
    1 yr

    Corporate Tech Support Specialist

    Karats and Company LLC
    • Provided network security support including incident response and vulnerability analysis across cloud infrastructure and a distributed endpoint fleet.
    • Built and automated troubleshooting tools that resolved 90%+ of support inquiries on first contact. Reduced ticket volume and demonstrated early instincts for automation.
    • Collaborated cross-functionally to identify and mitigate threats. The kind of cross-disciplinary work that defines modern AI and security teams.
  4. Jan 2020 - Aug 2023
    Charlotte, NC
    3.5 yrs

    HR Generalist / Information Systems Specialist

    Vector Fleet Management, LLC
    • Designed and maintained large-scale data storage systems for high-volume operational data. Built the data architecture instincts that translate directly to vector databases and AI retrieval pipelines.
    • Led a company-wide data visualization overhaul in Tableau, creating interactive dashboards that cut analysis time by 20% and accelerated decision-making across departments.
    • Operated independently on complex technical and organizational problems, demonstrating the self-direction essential for AI engineering work.
  5. Nov 2005 - Aug 2010
    Active Duty · Veteran
    5 yrs

    Security Forces Specialist

    United States Air Force
    • Trained and operated under high-stakes, mission-critical conditions. The foundation for the discipline, threat-modeling instinct, and adversarial mindset I apply to AI system design today.
03 / Selected work

Things I'm actually shipping.

A live look at what's running on my own hardware right now — production-grade edge AI, distributed inference, and the AI/security research backing it. A polished portfolio site goes here next.

Live99 vs 5

Agentic Phishing Triage System

LangGraph-orchestrated multi-agent pipeline that ingests a raw email and returns a 0–100 risk score with a plain-language verdict. Specialized agents handle header forensics (SPF/DKIM/DMARC), social-engineering analysis, and verdict synthesis. Cleanly separated phishing from legitimate mail (99/97 malicious vs. 5/4 benign) and caught a BEC gift-card scam that passed email authentication — proving content analysis matters alongside headers. Built with explicit data/instruction separation as an adversarial-security design.

LangGraphMulti-AgentClaudeOpenRouterPython
View project
Live25 fps · 100ms

Edge AI Home Security Platform

Production-grade surveillance running entirely on local hardware. Reolink PoE camera streams into a Raspberry Pi 5 and Hailo-8 NPU executing YOLOv8s at 25fps with ~100ms inference. GStreamer pipeline, SQLite event logging, Flask REST API (9 endpoints), Telegram alerts, and systemd services. Tuned with persistence buffers and ROI masking to suppress false positives.

YOLOv8Hailo-8 NPUGStreamerFlasksystemd
Live0 cloud calls

Distributed Two-Pi AI Architecture

Edge system over LAN. Pi #1 handles inference and serves a detection API. Pi #2 runs Ollama (Llama 3.2) and a SOC-themed dashboard consuming that API. Fully on-device with zero cloud dependency and zero exfiltration.

Edge AIOllamaLlama 3.2RESTLAN
LiveReal-time

SOC Security Dashboard

Security Operations Center-style monitoring console with a dark theme, real-time KPI tiles, Plotly visualizations, modal AI assistant, and forensic history view. Streamlit MVP shipped on Pironman Pi; React/JSX migration in flight for production polish via Netlify.

StreamlitReactPlotlySOC
LiveZero exfil

Conversational AI Security Analyst

Local Llama 3.2 wired to a context-injection pipeline that feeds live detection stats. Enables natural-language queries about security data entirely on-device.

Llama 3.2Context InjectionOn-device
Live

LLM API Engineering

Active development against the OpenAI and Anthropic APIs. Structured outputs, prompt engineering, agentic workflows, and the production patterns that take a prototype to a system you can trust.

OpenAIAnthropicStructured Outputs
In Progress

Agentic AI Engineering

Multi-agent systems built with the OpenAI Agents SDK, CrewAI, LangGraph, and AutoGen. Includes a Deep Research agent and a 4-agent engineering team coordinating real work.

Agents SDKCrewAILangGraphAutoGen
In Progress

RAG Pipelines

Vector database integration (Chroma, FAISS) for context-aware AI applications. Chunking, embedding strategy, retrieval evaluation, and the observability layer to keep it honest.

ChromaFAISSEmbeddings
Live

GRIND - AI-Powered Wellness PWA

React/JSX progressive web app integrating WHOOP biometric data via OAuth2. Real-time sync of Recovery, HRV, RHR, Strain, Sleep, and Calories with a conversational wellness assistant. Deployed to Netlify.

ReactWHOOP APIOAuth2PWA
View project
In Progress

The Grail CLT - AI Sneaker Valuation

React-based pricing platform for the sneaker collecting community. AI valuation engine and market trend analysis with an editorial dark aesthetic.

ReactAI PricingNetlify
Live

cortneybowman.dev — AI-Assisted Portfolio

This site. Built with Next.js 16, React 19, TypeScript, and Tailwind CSS — engineered through human-AI collaboration in Cursor. Demonstrates the working pattern I apply across every project: clear architectural intent, AI as implementation partner, human judgment on the bar for production quality. Deployed via continuous integration.

Next.jsReactTypeScriptTailwindCursor
View project
Live

Security x AI Research

Cybersecurity lens applied to AI: prompt injection, adversarial vision attacks against the YOLOv8 pipeline I run in production, and secure LLM deployment patterns. Backed by 5+ years of threat analysis experience.

Prompt InjectionAdversarial MLAppSec
Reserved

Full portfolio incoming.

Detailed case studies — architecture diagrams, evaluation results, and the stories behind the systems — are landing here.

→ /portfolio · soon
04 / Stack & credentials

The tools, the training, the receipts.

AI / ML
  • ›OpenAI API
  • ›Anthropic API
  • ›Llama 3.2 (Ollama)
  • ›YOLOv8
  • ›Hailo-8 NPU
  • ›GStreamer
  • ›RAG (Chroma, FAISS)
  • ›Agentic Workflows
  • ›Prompt Engineering
  • ›Adversarial ML
Engineering
  • ›Python
  • ›TypeScript / React
  • ›Next.js
  • ›Flask REST APIs
  • ›SQLite
  • ›systemd
  • ›Linux
  • ›Git / GitHub
  • ›Netlify
Data & Analytics
  • ›Microsoft Power BI
  • ›Power Automate
  • ›Microsoft Copilot
  • ›Copilot Studio
  • ›Tableau
  • ›Plotly
  • ›Streamlit
  • ›Vector DBs
Security
  • ›Threat Detection
  • ›SIEM
  • ›MITRE ATT&CK
  • ›Zero Trust
  • ›Incident Response
  • ›Vulnerability Analysis
  • ›Phishing Simulation
Education
  • M.S. Management Information Systems
    Keller Graduate School of Management - DeVry University
    Information Security Specialization · 4.0 GPA
    Sept 2024
  • B.S. Computer & Information Sciences
    DeVry University
    Software, systems, and applied development
    Jan 2020 - Aug 2023
  • Certificate in Cybersecurity
    CodePath
    Hands-on offensive & defensive fundamentals
    Feb - May 2024
Certifications
Microsoft Certified - Power BI Data Analyst Associate (PL-300)Microsoft Certified - Power Platform Fundamentals (PL-900)AWS Cloud PractitionerGoogle Cybersecurity CertificateMITRE ATT&CKFoundations of CybersecurityIntroduction to Software, Programming & DatabasesTools of the Trade: Linux & SQLInformation Technology Fundamentals
Honors
  • ★Alpha Chi National Honor Society
  • ★Delta Mu Delta International Honor Society
  • ★PMI Member
  • ★DeVry Cultural Inclusion Badge
05 / Contact

If you're building applied AI or agentic systems — let's talk.

Open to AI engineering roles, contract work, and serious collaborations on RAG, edge inference, and secure LLM systems.

cbowman706@gmail.com→LinkedIn ↗
Currently in Charlotte Metro, NC