Currently an Extern @Pfizer
UC Davis chemistry undergraduate and AI developer combining organic synthesis expertise with custom RAG workflows to innovate data-driven scientific research
Explore my journey into artificial intelligence: how I went from writing my first lines of code to building intelligent document retrieval systems and RAG workflow.
Pfizer · Aug 2026 · ✅ Verified by Extern
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
UC Davis chemistry undergraduate and AI developer combining organic synthesis expertise with custom RAG workflows to innovate data-driven scientific research
I currently study chemistry at UC Davis, managing both research about lipid nanoparticles and interest in patent law. Recently, I've gained interest in AI and machine learning, so I took initiative in participating in an innovative externship focused on AI-powered document insights.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Experience
Undergraduate Researcher
UC DAVIS, FRANZ LAB · Sep 2025 – Present
Vice President
KOREAN AMERICAN STUDENT ASSOCIATION (KASA), UC DAVIS · Sep 2025 – Present
Shift Lead
TOMO TEA HOUSE · Sep 2025 – Present
Professional Development Associate
DAVIS PRE-LAW SOCIETY · Jun 2026 - Jun 2027
Head of Marketing Strategy, Head of Research, Project Manager
CODOLOGY · Oct 2022 – Jul 2024
Researcher
ASDRP, NJOO LAB · Jun 2023 – Jun 2024
Education
UNIVERSITY OF CALIFORNIA, DAVIS
Bachelor of Science in ACS Chemistry; Minor in Political Science · Class of 2028
Skills
✅ Verified by Extern
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 externship prototyped AI document intelligence for pharmaceutical PDFs, documenting tokenization and Transformer context, cleaning structured and scanned-image data, extracting text and bounding boxes with PyMuPDF, comparing OCR engines, and building a LlamaIndex RAG chatbot. Deliverables included runnable Colab notebooks, processed images, extraction artifacts, OCR comparison results, and
.jpg)
Produced runnable Colab notebooks and artifacts: explanatory notes on tokenization and Transformers, cleaned structured and scanned-image data, extracted field-level text and bounding boxes from multi-page PDFs, compared three OCR engines, and implemented and evaluated a LlamaIndex RAG chatbot with tuned retrieval settings.
