Currently an Extern @Pfizer
Sophomore at UC Riverside, hands-on with OCR, LLMs, and retrieval-augmented generation through a Pfizer externship.
Portfolio projects focus on prototype systems for document parsing and data extraction, using OCR, LLMs, and retrieval-augmented generation to process enterprise PDFs.
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.
Personal Project · Oct 2026
Built LED sensor circuits using Arduino Uno and C++ programming; Designed and assembled an automated sensor-based water dispenser system; Applied soldering, circuit wiring, and breadboarding to create functional prototypes; Debugged hardware/software issues through testing and iteration
Sophomore at UC Riverside, hands-on with OCR, LLMs, and retrieval-augmented generation through a Pfizer externship.
I am a second-year Electrical Engineering student at the University of California, Riverside. I have limited formal work experience and am building practical skills through projects and an externship focused on AI, OCR, and document data extraction.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Experience
Operations Assistant
NIKO Car Seat Covers
Education
University of California, Riverside — Riverside, CA
Bachelor of Science in Electrical Engineering (Expected Graduation: 2029) · Class of 2029
Thousand Oaks High School — Thousand Oaks, CA
Graduated · 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 for enterprise PDF workflows using OCR, RAG, and LLM concepts. Deliverables included an explanatory write-up on tokenization and transformer attention, runnable Colab notebooks that cleaned messy files and produced OCR-ready images, and a Python pipeline that extracted dates, vendor names, and document types into a structured dataset.
.jpg)
I wrote an explanatory submission on tokenization and transformer attention, produced runnable Colab notebooks that cleaned messy files and prepared OCR-ready images, and built a Python pipeline that extracted dates, vendor names, and document types from multi-page SDF PDFs into a structured dataset.
The submission explained that LLMs broke text into tokens, used transformer attention to relate tokens, and learned patterns from data over time to improve next-token prediction and generate coherent text.
The project collected messy document files, parsed nested JSON into tabular rows, cleaned and standardized text with Python and Pandas, and applied image preprocessing (denoise, histogram equalization, thresholding) to produce cleaned data and OCR-ready images.
I processed multi-page SDF PDFs with Python, used PyMuPDF to extract text and bounding boxes, applied regex and position checks to locate dates and vendor fields, and produced a structured dataset of extracted fields.
Built LED sensor circuits using Arduino Uno and C++ programming; Designed and assembled an automated sensor-based water dispenser system; Applied soldering, circuit wiring, and breadboarding to create functional prototypes; Debugged hardware/software issues through testing and iteration
Built LED sensor circuits using Arduino Uno and C++ programming; Designed and assembled an automated sensor-based water dispenser system; Applied soldering, circuit wiring, and breadboarding to create functional prototypes; Debugged hardware/software issues through testing and iteration
