Pfizer logoCurrently an Extern @Pfizer
Le Thong Tan portrait

Mathematics student exploring AI and data extraction

Junior math major at Knox College, learning applied AI through a Pfizer externship in document insights and data extraction.

Work samples

Portfolio of coursework and work from the Pfizer Advanced externship, showing applied experience with AI methods for document insight and data extraction.

  • Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
    Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
    Pfizer logo

    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.

    AI & MLPythonDocument IntelligencePresentation Skills

About me

Junior math major at Knox College, learning applied AI through a Pfizer externship in document insights and data extraction.

I am Tan Le, a junior at Knox College studying mathematics. I have limited formal work experience and I'm completing the Pfizer Advanced: AI-Powered Document Insights & Data Extraction externship while finishing my bachelor's degree.

Externships

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

Pfizer

Education

Knox College

B.S. Mathematics · Class of 2028

Skills

Mathematics (undergraduate)AI concepts applied to document analysisData extraction workflowsProblem solvingAcademic research and coursework

✅ 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.

AI & MLPythonDocument IntelligencePresentation Skills

Overview

The project prototyped AI-powered document intelligence workflows combining OCR, retrieval-augmented generation, and large language models to extract structured data from enterprise PDFs. The work surveyed LLM architectures and evaluation methods, designed component interactions for OCR and RAG, and produced written explanations of model behavior and limitations.

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

What I've accomplished

I documented the technical foundation behind the prototype and summarized how core components fit together. Below are the specific deliverables I produced for the externship.

Project breakdown

View all work