RESEARCH INTERESTS

Agentic AI governance frameworks and orchestration architectures for enterprise and public-sector environments; responsible AI deployment in resource-constrained federal agencies; explainability, fairness, and bias mitigation in large language models and NLP systems; AI/ML applications in cybersecurity, information governance, and digital transformation; applied deep learning and transformer-based architectures for real-world operational problems.

---

ACADEMIC & APPLIED RESEARCH PROJECTS

Mental Health Analysis via Textual Analytics 2025
Research Project — George Washington University | GCP GPU Clusters

• Designed and trained BERT-based deep learning neural network with Self-Attention for mental health classification from text
• Addressed algorithmic bias, explainability, and fairness using PyTorch on Google Cloud GPU infrastructure
• Applied transformer architectures to clinical and social text corpora; benchmarked against baseline NLP models

Tsunami Prediction System — ML Pipeline & Flask Web Application 2026
Independent Applied ML Project | github.com/jtunnessen/tsunami-prediction-system | Azure App Service

• Designed and deployed an end-to-end ML application predicting tsunami likelihood from seismic activity data (magnitude, depth, intensity) using a Decision Tree Classifier optimized via GridSearchCV
• Achieved 89.83% accuracy and 89% tsunami recall (catch rate); best parameters: max_depth=10, criterion=’gini’
• Built automated preprocessing pipeline using Scikit-Learn Pipelines with StandardScaler, OneHotEncoder, and missing value imputation; serialized via Joblib for production inference
• Wrapped model in a Flask web application with interactive HTML/CSS interface for real-time earthquake parameter input and prediction; deployed to Azure App Service via CLI
• Demonstrates full ML lifecycle: data ingestion, preprocessing, hyperparameter tuning, model serialization, web integration, and cloud deployment
• Tech stack: Python 3.9, Scikit-Learn, Pandas, Flask, Seaborn/Matplotlib, Gunicorn, Azure App Service

Cybersecurity Analysis & Documentation AI Agent 2026
National Endowment for the Arts | NEA Production Deployment

• Designed and deployed a purpose-built agentic AI system integrating NIST 800-53 rev 5, OWASP Top 10 for 2025, MITRE ATT&CK, MITRE CVEs, and CISA KEV
• First production deployment of an agentic compliance automation system at a federal cultural agency
• Anchors published research on purpose-built vs. large-scale model thesis (Forbes Technology Council, 2026)

GitHub README Generator — Purpose-Built Agentic System 2026
National Endowment for the Arts | NEA Production Deployment

• Deployed small, task-specific LLM agent for automated developer documentation generation
• Demonstrated applied thesis: purpose-built models outperform generalist LLMs on constrained, high-frequency tasks

Section 508 Analysis & Documentation AI Agent 2026
National Endowment for the Arts | NEA Production Deployment

• Deployed small, task-specific LLM agent for automated accessibility compliance analysis
• Demonstrated applied thesis: purpose-built models outperform generalist LLMs on constrained, high-frequency tasks

DevtoDeployment — Multi-Agent Python Application 2026
Gradient Descent LLC | GCP: Cloud Run, Pub/Sub, Firestore, GCS, Secret Manager

• Architected multi-agent orchestration system using Python 3.12, LangGraph, and Google Cloud Platform
• Integrated OpenClaw agentic gateway via Telegram; Anthropic Claude API as primary LLM backend

Ipsum NLP Auto-Transcription & Translation Tool 2019
Voice of America | USAGM

• Designed and deployed NLP tool achieving 10x transcription and translation speed improvement
• Adopted by four international media organizations; scaled across 20+ language services serving 275M+ weekly viewers

Whole Genome Sequencing Cloud Re-Architecture 2016
USDA Food Safety and Inspection Service | Cloud Shared Service with FDA & CDC

• Led cloud migration and re-engineering of WGS infrastructure, yielding $12M per year in cost savings
• Established first federal cloud shared service for genomic data spanning USDA, FDA, and CDC