Pfizer
✅ Verified by Extern · ⏱️ In progress
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
Overview
The externship focused on prototyping AI document-intelligence workflows for enterprise PDFs, combining OCR, retrieval-augmented generation, and LLM techniques. The work summarized technical foundations, compared model approaches, and produced explainable notes on LLM architectures and their components.
What I've accomplished
I classified documents from a vendor file into quality, compliance, and technical categories, cataloged date formats present, and determined that pages lacked machine-readable text, requiring OCR for structured-data extraction.
Project breakdown
I inspected the provided vendor file, classified documents (quality, compliance, technical), cataloged date formats found, and noted that pages lacked machine-readable text so OCR was required to extract structured data.
