Currently an Extern @Pfizer
I build practical AI-powered document extraction and analysis solutions and am evaluating a shift in my career focus.
Portfolio items show work from the Pfizer Advanced externship and related efforts applying machine learning and data extraction to real documents.
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.
I build practical AI-powered document extraction and analysis solutions and am evaluating a shift in my career focus.
I am Sri Ramya Hanumanthu. I began my career and am now exploring a new direction. I recently completed the Pfizer Advanced: AI-Powered Document Insights & Data Extraction externship, where I focused on AI methods for extracting and analyzing document data.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Experience
Intake and Informatics Analyst
Excel Care Home Health · Jun 2026 - Dec 2027
Health Informatics Analyst — Data Analysis & Reporting
STENZO TECH · Aug 2025 - Dec 2025
Clinical Documentation & Health Information Associate — Clinical Chart Review
Surya Global Multi Specialty Hospital · Oct 2020 - Dec 2023
Education
Governors State University
Master of Science in Health Informatics · Class of 2025
Nova College Of Pharmaceutical Education & Research
Doctor of Pharmacy Pharm. D · Class of 2023
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 externship prototyped AI-powered document intelligence for enterprise PDF workflows, combining OCR, retrieval-augmented generation, and large language models. The work surveyed LLM architectures, input/encoding constraints, and common OCR-to-LLM pipelines, and documented tradeoffs for applying these techniques to PDF extraction and question answering.
.jpg)
I explained LLM tokenization, the Transformer self-attention mechanism, next-token generation, and the roles of training, fine-tuning, and human feedback in improving model outputs for pharmaceutical documents.
I explained how LLMs tokenized text, used the Transformer self-attention mechanism to learn token relationships, and generated responses by predicting next tokens. I noted training, fine-tuning, and human feedback as steps to improve outputs.
