M.S. candidate in Psychology: Data Science in Human Behavior at UW–Madison (expected Dec 2026); B.S. in Psychology (neuroscience concentration, sociology minor) from UW–Parkside. I build AI systems from start to finish: multi-agent document pipelines, transformer fine-tuning and calibration, LLM evaluation, computer vision classification, and behavioral prediction models. My capstone, with industry partner American Family Insurance, looks for ways to cut the cost of AI inference and improve document processing. I also bring five years of high-volume logistics and operations work in quality assurance, documentation, and process improvement.
Digital-MailroomDSHB Capstone project — American Family Insurance (industry partner)
Capstone with American Family Insurance to improve how documents are read, sorted, and managed: 10 Python packages covering entity extraction, classification, routing, and scalable workflows.
Designed and built one LangGraph pipeline that joins legal-document routing, prompt experiments, deterministic scoring, dataset management, and deployment in a reproducible Docker environment.
Mailroom-MLML Training, Evaluation & Fine-Tuning
Built a ModernBERT document classifier with training, evaluation, and fine-tuning pipelines, including data lineage tracking, probability calibration, and production routing logic.
Wrote PyTorch training pipelines with Transformers and Hugging Face datasets, evaluated with scipy, and exported to ONNX for FastAPI serving on Modal. Kept pytest coverage throughout.
Built a Python toolkit that converts TIFF/PDF pages to 300-DPI images, runs OCR, and sorts documents into 16 RVL-CDIP categories using OpenRouter vision models.
Ran 17+ prompt iterations and produced confusion matrices, misclassification analyses, and cost projections to choose prompts and models on evidence.
Psychometric Digital TwinBehavioral ML Research | UW–Madison
Built a behavioral prediction pipeline on 241 analysed survey respondents (252 matched). Ridge, Elastic Net, k-NN, Random Forest, histogram gradient boosting, XGBoost, and MLP models predicted communication-apprehension scores from demographic, employment, geographic, and transit features, with cross-validation and SHAP feature importance.
Checked the PRCA’s psychometric structure with factor analysis, then built LLM “digital twin” personas with tiered embodiment prompts (OpenRouter/vLLM). Benchmarked them against the ML baselines on shared metrics (MAE, band accuracy, F1) and analyzed systematic bias by demographic group.
Education
University of Wisconsin–MadisonMadison, WIExpected Dec 2026
M.S. Candidate — Psychology: Data Science in Human Behavior · GPA 3.85
Graduate work in machine learning, statistics, behavioral data analysis, predictive modeling, experimental design, and publication-quality visualization.
University of Wisconsin–ParksideKenosha, WISep 2020 – May 2025
Minor in Sociology; Provost’s List (7x), Dean’s List (8x), Distinguished Achievement Award (2025), and Psychological Research Certification (300 lab hours).
Conducted cognitive neuroscience research under Dr. Melissa Gregg: designed and pilot-tested a study of perceptions of chatbot truth, deception, and user cognitive workload (code: github.com/Exios66/truth-deception-architecture).
Ran EEG systems and analyzed neural time-series data to measure brain activity, adding signal-processing and statistical analysis to existing lab research on sleep quality and cognitive load.
Presented findings at the 2025 Midwestern Psychological Association conference.
Keep recreation and wellbeing centers across campus clean, safe, and ready for use.
Fix facility and equipment problems across multiple locations so centers stay safe and open during peak hours.
Worked with operations and event staff to resolve facility problems quickly and limit disruption for students, staff, and visitors.
Avis Budget Group — DriverMadison, WIJun 2026 – Present
Move, stage, and safety-check rental vehicles across a 500+ vehicle fleet so cars are ready and on time across the rental network.
Coordinate vehicle moves between locations and uphold fleet safety standards.
Meijer Distribution — Logistics CoordinatorPleasant Prairie, WIJul 2020 – Dec 2025
Promoted from Retail Loader to Logistics Coordinator for reliable quality assurance and data-driven process documentation in high-volume operations.
Analyzed quality-assurance data for 64 daily outbound trailers across the Midwest regional network and held error rates below 1% through root-cause investigation and process refinement.
Worked with warehouse and transportation teams to find quality problems and resolve logistics exceptions before shipment.
Research Training
CITI Program: Conflicts of Interest training 2025
CITI Program: IRB Training for Students and Faculty 2025