Currently an Extern @Pfizer
I design and ship prototypes that extract insight from PDFs using OCR, LLMs, and RAG, demonstrated in a Pfizer externship.
🟢 Open to workPortfolio includes a Pfizer externship prototype: an AI-powered document intelligence system that automated enterprise PDF tasks using OCR, LLMs, and RAG.
.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.
I design and ship prototypes that extract insight from PDFs using OCR, LLMs, and RAG, demonstrated in a Pfizer externship.
I build prototype AI tools that turn enterprise documents into searchable, structured data. I completed a Pfizer externship where I used OCR, large language models, and retrieval-augmented generation to automate PDF workflows and create a portfolio-ready prototype. I'm early in my career and exploring directions that blend applied ML and product-focused engineering.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Experience
Product Management & Design
Freelance · Jun 2025
Operations Associate (Product Analyst)
Napier Park Global Capital · Oct 2022 - May 2025
Associate
Bowery Valuation · Apr 2021 - Sep 2022
Tax Consultant (Analyst)
Deloitte · Aug 2019 - Jun 2020
Education
Georgetown University
B.S.F.S., Global Business · Class of 2019
Designlab
UX Academy · Class of 2025
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 work prototyped AI-powered document-intelligence workflows for enterprise PDFs, combining OCR, LLMs, and RAG. The project reviewed model architectures, mapped information-extraction steps, and documented technical components and integration choices. The deliverables explained LLM tokenization, Transformer self-attention, pretraining, and fine-tuning for pharmaceutical documents.
I produced a technical explanation of how LLMs tokenize text, apply Transformer self-attention to model context, predict next tokens, and how pretraining and task-specific fine-tuning operate for pharmaceutical documents.
I explained how LLMs tokenized text, used Transformer self-attention to model context, and predicted next tokens. I described pretraining on large unlabeled corpora and subsequent fine-tuning on smaller task-specific datasets.