Currently an Extern @Pfizer
Currently a sophomore at the University of Minnesota, I am passionate about leveraging technology to solve real-world problems in engineering.
Discover my projects that highlight my skills in electrical engineering and my commitment to innovation and problem-solving.
.jpg)
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.
Currently a sophomore at the University of Minnesota, I am passionate about leveraging technology to solve real-world problems in engineering.
I am a sophomore at the University of Minnesota, pursuing a Bachelor's Degree in Electrical Engineering. With some work experience under my belt, I'm eager to officially kick off my career and enhance my competitiveness in the job market.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
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 pharmaceutical PDFs, combining OCR, NLP, and LLM concepts with Python extraction techniques. Deliverables included a technical summary of LLM tokenization and attention, a Colab notebook that cleaned and flattened messy text into structured DataFrames, and a pipeline that extracted field-level values and bounding boxes from multi-page SDF
I produced a technical summary of LLM tokenization and attention, a Google Colab notebook that cleaned and flattened messy text into structured DataFrames, and a Python extraction pipeline that output field-level values and bounding boxes from multi-page SDF PDFs.
I summarized how LLMs tokenized text, used the Transformer attention mechanism to model context, and learned by adjusting billions of parameters. I noted continued improvement via further training, human feedback, and fine-tuning.
In a Google Colab notebook I cleaned messy text with ftfy, BeautifulSoup, emoji removal, contractions expansion, regex standardization, and saved a cleaned text file. I also implemented JSON flattening for nested records to produce a structured DataFrame.
The project converted multi-page SDF PDFs into machine-readable data. I used Python in a Colab notebook to extract text, bounding boxes, and field-level values (dates, vendor, doc type, revision, signature timestamp) and output structured records.
I ran Tesseract, PaddleOCR, and EasyOCR on the same scanned supplier PDF, inspected output differences, and documented accuracy, layout preservation, setup issues, and edge cases. The deliverable concluded PaddleOCR read labels and values together best, with Tesseract catching some sideways text.