Currently an Extern @Pfizer
Sophomore at UNC Charlotte who designs prototypes that extract and summarize data from real documents using OCR, LLMs, and retrieval techniques.
Portfolio of applied projects, including a Pfizer externship where I built an AI document insights and data extraction prototype using OCR, LLMs, and retrieval-augmented generation.
.jpg)
Pfizer · ✅ Verified by Extern · ⏱️ In progress
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
Sophomore at UNC Charlotte who designs prototypes that extract and summarize data from real documents using OCR, LLMs, and retrieval techniques.
I am Matt Ruppert, a sophomore studying Finance at UNC Charlotte and the founder of BuiltToScale. I work as Lead Sales Representative and Event Coordinator at HOTWORX and previously estimated projects and apprenticed as an electrician at R-Mar Electric. I build practical skills in financial modeling, Python, SEO, prompt engineering, CRM tools, and Office, and I’m exploring AI document extraction through a Pfizer externship.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Experience
Founder and Owner
ZTECH MEDIA · Jan 2023 – Present
Lead Sales Representative & Event Coordinator
HOTWORX · Oct 2024 – May 2026
Project Estimator / Electrician Apprentice
R-MAR ELECTRIC · Nov 2020 – Aug 2023
Education
UNIVERSITY OF NORTH CAROLINA AT CHARLOTTE: Belk College of Business
Bachelor of Science in Business Administration, Finance Concentration
CENTRAL PIEDMONT COMMUNITY COLLEGE
Accounting and Finance
Skills
✅ Verified by Extern · ⏱️ In progress
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
The project prototyped AI-powered document intelligence components for enterprise PDF workflows, combining optical character recognition, large language models, and retrieval-augmented generation. The work surveyed LLM architectures and OCR integration patterns, then documented approaches for extracting and structuring data from complex PDFs.
I researched technical foundations and integration patterns for LLM-driven document processing, then summarized findings and practical approaches for extracting structured data from PDFs.