Currently an Extern @PfizerI'm a UMass Amherst senior specializing in Biomedical Engineering, ready to tackle real-world challenges with innovative solutions.
Explore my work in biomedical engineering, including AI-driven document insights and data extraction for real-world applications.
.jpg)
Pfizer✅ Verified by Extern⏱️ In progressPrototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
I'm a UMass Amherst senior specializing in Biomedical Engineering, ready to tackle real-world challenges with innovative solutions.
I am a senior at the University of Massachusetts Amherst pursuing a Bachelor's Degree in Biomedical Engineering. My journey is just beginning, but I'm eager to apply my skills and knowledge in innovative ways.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Experience
Extern
Pfizer · July 2026 – Present
Undergraduate Research Assistant
He’s Advanced Analytical Lab · September 2024 – Present
Biotechnology & Bioentrepreneurship Summer Intern (B2BB)
Morehouse School of Medicine · May 2026 – July 2026
Biomedical Engineering Intern
Gao Research Group · June 2025 – August 2025
Education
University of Massachusetts Amherst
B.S. Biomedical Engineering · Class of 2027
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 examined how AI systems read and represent pharmaceutical documents, combining NLP, LLM concepts, and OCR techniques. The project summarized how text is converted into numerical vectors, how models are trained on corpora to predict or fill tokens, and how vectors are decoded into human-like output. The deliverable documented these mechanisms as they apply to scanned and born-digital
I produced a technical explanation showing how LLMs convert text into numerical vectors, are trained to predict or fill tokens, learn language patterns, and decode vectors back into human-like text.
I described how LLMs converted input text into numerical vectors, were trained on corpora to predict next tokens or fill gaps, learned language patterns and grammar, and decoded vectors to generate human-like output.
The externship module required Python work in Colab. I ran notebooks to create data structures, clean tabular data with pandas, parse nested JSON into dataframes, standardize text (including unicode and contractions), and apply denoising, contrast and thresholding to a scanned document. The…