🟢 Open to work
Masters student at Temple University with hands-on externship experience building AI-powered document analysis and data extraction solutions.
Projects and externship work focused on applying AI to extract data from documents and generate actionable insights, using practical methods learned during my Pfizer Advanced externship.
.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.
Masters student at Temple University with hands-on externship experience building AI-powered document analysis and data extraction solutions.
I am Nahja Brown, a graduate student at Temple University pursuing a master's degree in Bioinformatics. I have some work experience and completed the Pfizer Advanced: AI-Powered Document Insights & Data Extraction externship, where I worked on AI document analysis and data extraction tasks.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
In progress
Experience
Disability Services Specialist
National Board of Medical Examiners (NBME) · December 2024 – August 2026
Certified Pharmacy Technician (CPhT)
CVS Health · August 2024 – August 2025
Customer Support Specialist
Healthmonix · November 2023 – March 2024
Service Operations Advisor (Level P2)
Permutive Technologies · March 2022 – May 2023
Customer Service Representative
Maximus · February 2020 – June 2020
Point of Sale (POS) Operator
Burlington · August 2019 – November 2019
Education
Temple University
Professional Science Master's, Biological Data Science. · Class of 2027
Arizona State University
Bachelor of Science, Biological Science.
HubSpot
SEO Marketing Certification.
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 workflows for enterprise PDFs, combining OCR, large language models, and retrieval-augmented generation. The work researched LLM fundamentals and applied that knowledge when designing document-processing components. Deliverables included technical summaries and explainers used across the prototype.
I produced a technical writeup that explained how large language models tokenize input, learn patterns during training, and use token prediction to generate humanlike text for document-inspection workflows.
The submission explained that large language models generated humanlike text by tokenizing input and learning patterns through training phases, and it described how models used token prediction to formulate responses.
