Skip to content

Open to research collaborations and 2027 engineering roles

I build systems where research turns into production code.

I’m a PhD researcher at the University of Maryland Eastern Shore and a full-stack developer. Right now I work on a multi-user VR classroom for Meta Quest headsets, where each 50-minute class runs as a cycle of lecture video, challenge, and debrief. We tested it this November in a live class of six students, with me hosting the server and handling builds. I also build the scenes in Blender and lead a team of two. Outside the classroom project, I’ve built an LLM agent that acts on live security alerts and an unsupervised detection pipeline running on a real Active Directory domain.

  • +Applied AI on local, self-hosted models
  • +Detection engineering and Zero Trust systems
  • +GPU and parallel computing

Currently building

Active work

  • In progressAI / ML

    Adaptive AI Educator

    Building the podcast format for a multi-format learning platform

    ElevenLabsBlenderThree.jsTypeScriptWebGL
  • In progressXR

    Multi-User VR Classroom

    A shared classroom for Meta Quest, built around lecture, challenge, and debrief

    TypeScriptThree.jsIWSDKWebXRPostgreSQL+4

Selected work

Things I built and measured

all work ->
01Web2026Live

Temple Display Board

A live event board and daily notification job for a community temple

A fullscreen display for the Hindu Temple of Eastern Shore in Salisbury, running unattended on a TV in the building. It shows the current month's events and the people sponsoring them, and it updates the moment the data changes. Behind it, a scheduled job checks each morning for anything happening that day and reports what it did.

Next.js 16TypeScriptReact 19Tailwind CSSshadcn/ui+6
Live
Realtime updates
02Security2026

LLM Agent for Threat Hunting

A local language model that triages a live security alert stream

A threat-hunting agent that builds a running profile of each user from a live Wazuh alert stream, then prompts a locally hosted Qwen2.5-7B with that frequency and business-hours context. The reply is constrained to JSON carrying severity, confidence, and a recommended response action, so a SOC pipeline can route it without a human reading prose first.

PythonOllamaQwen2.5-7BWazuhJSON Schema
100%
Local inference
03AI / MLSpring 2026

Insider Threat Detection from Windows File-Share Events

Unsupervised ML on 4656/5145 telemetry in a live Zero Trust lab

Windows domains emit file-access telemetry constantly. Events 4656 and 5145 record who touched what, from where, and whether access was granted, and almost nobody looks at it. This work builds an unsupervised detection pipeline on that stream inside a controlled Active Directory lab, folding raw events into behavioral sessions and scoring them with Isolation Forest, LOF, and One-Class SVM.

Pythonscikit-learnSHAPWindows Server 2022Active Directory+1
18,572
Events collected
04SystemsMar 2025

GPU Acceleration for Cryptanalysis

AES-128 key search, CUDA against OpenMP, measured

A direct measurement of what wide parallelism does to brute-force cryptanalysis. The same AES-128 key search was written twice, once with OpenMP across 8 CPU threads and once in CUDA across 40,960 threads, then run over a 4.29 billion key space. CUDA finished in 123.5 seconds against OpenMP's 3,928, a 32x gap on a laptop GTX 1050.

CUDAOpenMPC / C++AES-128
32x
Speedup

Publication

HCII 2026

Adaptive AI Educator: A Multi-format Learning Platform for Aquatic Invasive Species Education and Outreach - A Blue Catfish Case Study

Sagar Patel, Beryl Malomo, Yixiao Ma, Jaden Hanson, Chengchu Liu, Lizhou Cao (2026).HCII 2026. Lecture Notes in Computer Science, vol. 16733, pp. 596-613. Springer.

Presented at HCII 2026 | First Authordoi:10.1007/978-3-032-30784-2_37

Toolkit

What I work with

AI & Machine Learning

Local LLM inference (Ollama, Qwen2.5)LLM agent designConstrained JSON outputscikit-learnSHAP explainability

Languages

PythonTypeScript / JavaScriptC / C++CUDA CPHPSwiftSQL

Backend, Data & Cloud

Node / ExpressFlaskDjangoPostgreSQL (Supabase, RLS)MongoDBRESTJWTDockerCloudflareGit

Systems & Performance

CUDAOpenMPGPU computingConcurrent programmingMininet / Mininet-WiFiWindows Server & Active Directory