Currently an Extern @Pfizer
Aspiring Tech Professional
I blend business acumen with technology, currently exploring AI solutions at Pfizer to enhance data management.
Work samples
Explore my journey through projects in AI and data management, showcasing my skills and innovative approaches.
Pfizer · ✅ Verified by Extern · ⏱️ In progress
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
AI & MLPythonDocument IntelligencePresentation SkillsEagleCo AI Talent Acquisition Research
Spearheaded a talent acquisition restructuring project for a mid-size technology firm, reducing average time-to-hire by 58% through the identification and elimination of workflow bottlenecks. Engineered a strategic roadmap for incorporating Generative AI into talent acquisition process by analyzing industry standard recruitment cases, providing evidence-based recommendations to modernize hiring operations. Synthesized complex AI technical architectures into a comprehensive consulting report and executive presentation, enabling non-technical stakeholders to evaluate financial ROI and risk mitigation strategies.
NBA Fantasy Points Prediction
Led exploratory data analysis on 82,000+ NBA player records, identifying linear and non-linear relationships that shaped the team's model selection. Built and compared Linear Regression and Random Forest models, with the final approach outperforming baseline projections. Translated model outputs into clear Start/Bench/Cut recommendations, making complex statistical results actionable for non-technical users.
About me
I blend business acumen with technology, currently exploring AI solutions at Pfizer to enhance data management.
I am Daniel Daramola, a Business Computer Information Systems major at the University of North Texas. Currently, I am engaged in an externship at Pfizer, focusing on AI-powered document insights and data extraction. My goal is to leverage technology to drive innovation and efficiency in business processes.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Experience
Extern
Pfizer · June 2026 - Present
Data Analyst and Peer Mentor
University of North Texas · August 2024 – May 2026
Pre-Sales Solutions Architect Intern
Dell Technologies · June 2025 – August 2025
Data Analyst Intern
Reisty · June 2024 – October 2024
Education
University of North Texas
Bachelor of Science in Business Computer Information Systems · Class of 2026
Skills
✅ Verified by Extern · ⏱️ In progress
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.
Overview
In my externship with Pfizer, I developed an AI-powered document intelligence prototype that streamlines the processing of pharmaceutical documents. This project involved leveraging Optical Character Recognition (OCR), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) to automate workflows and enhance document insights, culminating in a comprehensive portfolio piece.
.jpg)
What I've accomplished
I produced a set of technical artifacts: explanations of LLM tokenization and attention, multiple Google Colab notebooks and a preprocessed scanned image, a JSON export of extracted text with bounding boxes, and an OCR comparison recommending a workflow.
Project breakdown
The submission explained how Large Language Models converted text into numeric token IDs, used self-attention to relate tokens across a sequence, scored token probabilities, and iteratively selected next tokens until a stop token ended generation.
The externship presented raw document data. I cleaned structured data with Pandas, normalized nested JSON, applied text cleaning and standardization, and used OpenCV/PIL image preprocessing to improve OCR input. Deliverables included multiple Google Colab notebooks and a preprocessed scanned image.
I extracted raw text and bounding boxes from an SDF using PyMuPDF, analyzed where extraction succeeded (labels like Expiration Date) and failed (tables and fragmented multi-word phrases), and produced a JSON-structured export showing text and bbox entries.
The project compared three OCR engines on a scanned pharmaceutical document. I ran each tool, recorded installation and output issues, and concluded PaddleOCR preserved layout best; I recommended a PaddleOCR-first workflow with targeted Tesseract fallbacks.
EagleCo AI Talent Acquisition Research
Spearheaded a talent acquisition restructuring project for a mid-size technology firm, reducing average time-to-hire by 58% through the identification and elimination of workflow bottlenecks. Engineered a strategic roadmap for incorporating Generative AI into talent acquisition process by analyzing industry standard recruitment cases, providing evidence-based recommendations to modernize hiring operations. Synthesized complex AI technical architectures into a comprehensive consulting report and executive presentation, enabling non-technical stakeholders to evaluate financial ROI and risk mitigation strategies.
NBA Fantasy Points Prediction
Led exploratory data analysis on 82,000+ NBA player records, identifying linear and non-linear relationships that shaped the team's model selection. Built and compared Linear Regression and Random Forest models, with the final approach outperforming baseline projections. Translated model outputs into clear Start/Bench/Cut recommendations, making complex statistical results actionable for non-technical users.