<jacky_lin>

/* Undergrad 27' @dku AI researcher molecular biophysicist */

username.png

Currently an Extern @Pfizer

<Work_samples>

Portfolio of prototypes using OCR, LLMs, and RAG to extract data and produce actionable insights from enterprise PDFs, including work from a Pfizer externship.

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
[01]Pfizer ExternshipJun 2026
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>

Undergrad 27' @dku AI researcher molecular biophysicist

I am Jacky Lin. I build AI-powered document intelligence prototypes that combine OCR, large language models, and retrieval-augmented generation to automate real enterprise PDF workflows. My work includes a Pfizer externship project focused on data extraction and document insights.

Externships

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

Pfizer

Education

Duke University

Molecular Bioscience · Class of 2027

Skills

OCRLarge language models (LLMs)Retrieval-augmented generation (RAG)PDF data extractionPrototype development

Back_to_works

Pfizer · Jun 2026 ↗

✅ Verified by Extern

<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

This externship built an end-to-end document intelligence prototype for pharmaceutical supplier documents, combining OCR, layout-aware extraction, and RAG retrieval. Work included text extraction, OCR comparisons, chunking and vector indexing, and a local Gradio chatbot. The final deliverable integrated these components and produced a Colab demo and Figma presentation.

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

Open Link

//What I've accomplished

I delivered an integrated pipeline that performs OCR and layout-aware extraction, classifies and splits multi-document PDFs, extracts structured fields into JSON, and supports RAG Q&A via a local Gradio app, packaged as a Colab demo and Figma walkthrough.

///Project breakdown

View_all_works

<Work_samples>

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

<About_me>

<Pfizer_Advanced:_AI-Powered_Document_Insights_&_Data_Extraction_Externship>

/Overview

//What I've accomplished

///Project breakdown

How AI Reads Pharmaceutical DocumentsI explained how large language models (LLMs) work, summarizing their architecture and training process.

Learn to Work with Python for AI-Powered Document ProcessingI prepared and cleaned pharmaceutical-style documents with Python, using Colab notebooks to process data, clean text, and preprocess images for OCR.

Data Extraction from Documents Using PythonI extracted word-level text and bounding boxes from a multi-page SDF using PyMuPDF and produced a structured JSON output.

Advanced OCR Comparison and Layout-Aware ExtractionI compared Tesseract, PaddleOCR, and EasyOCR on a scanned pharmaceutical supplier PDF and documented which engine handled layout and field extraction best.

Introduction to Retrieval-Augmented Generation (RAG)I built and evaluated a RAG pipeline using LlamaIndex to parse a technical PDF, create embeddings, run hybrid retrieval with reranking, and generate answers to certificate-focused prompts.

Advanced RAG and Open-Source ExperimentsI compared three RAG retrieval configurations on a pharmaceutical SDF PDF and reported which setup retrieved the most relevant chunks and produced the best answers.

Blob Processing, Classification, and RoutingI built a page-level classifier that split a 10‑page pharmaceutical PDF into 8 logical documents, labeled each page with doc_id and doc_type, and exported the results as assignment-ready JSON.

Gradio Chatbot with RAG IntegrationI built a Gradio document Q&A chatbot that processed PDFs, indexed chunks, and returned retrieval-grounded answers with UI controls and citation badges.