Pfizer logoCurrently an Extern @Pfizer
Roberto Sugira portrait

Computer Science junior building AI document tools

I prototype practical AI solutions for real documents, using OCR, large language models, and RAG to automate PDF workflows.

Work samples

Projects center on document intelligence, data extraction, and AI-driven automation. Highlights include a Pfizer externship prototype using OCR, LLMs, and RAG for PDF workflows.

  • Praytell — Content Management Database
    Praytell — Content Management Database

    Collaborated with faculty advisor Dr. Brent Reeves to design a full database system (15+ tables, 300+ fields) with 15+ SQL analytical views — translating stakeholder requirements into structured reporting and operational insights across geographic regions.

    PostgreSQLPostGISSQLGit
  • Epilepsy Diagnosis LLM — AI4All Program
    Epilepsy Diagnosis LLM — AI4All Program

    Collaborated equally with a team to build and evaluate an LLM classification model on Kaggle clinical data — handling data cleaning, model training, and architecture evaluation with full documentation for reproducibility.

    Pythonpandasscikit-learnHuggingFace

About me

I prototype practical AI solutions for real documents, using OCR, large language models, and RAG to automate PDF workflows.

I am a junior Computer Science student at Abilene Christian University pursuing a bachelors degree. I have limited formal work experience and I build technical projects to learn practical skills, including an externship project that used OCR, LLMs, and retrieval-augmented generation to prototype document intelligence workflows.

Externships

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

Pfizer

Experience

AI Extern

Pfizer · Feb 2026 – Present

Professional Development Student Coach

Abilene Christian University · Aug 2025 – Present

IT Support Assistant

Abilene Christian University — Information Technology · Aug 2024 – Present

Technology Fellow

Bridge2Rwanda · Mar 2023 – May 2024

Education

Abilene Christian University

B.S. Computer Science; BBA Finance · Class of 2028

Skills

OCRLarge language models (LLMs)Retrieval-augmented generation (RAG)PythonDocument data extraction

Praytell — Content Management Database

Collaborated with faculty advisor Dr. Brent Reeves to design a full database system (15+ tables, 300+ fields) with 15+ SQL analytical views — translating stakeholder requirements into structured reporting and operational insights across geographic regions.

PostgreSQLPostGISSQLGit
View all works

Epilepsy Diagnosis LLM — AI4All Program

Collaborated equally with a team to build and evaluate an LLM classification model on Kaggle clinical data — handling data cleaning, model training, and architecture evaluation with full documentation for reproducibility.

Pythonpandasscikit-learnHuggingFace
View all works

✅ 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 Skills

Overview

The externship explored building AI-powered document intelligence for enterprise PDFs, combining OCR, LLMs, and RAG components. The work surveyed LLM architectures, evaluation approaches, and integration patterns, then translated those findings into technical guidance for extracting and querying document data. Deliverables included a research brief and implementation notes on LLM behavior and

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

What I've accomplished

I researched core LLM concepts and explained how they behave in document-processing pipelines. Below are the concrete outputs I produced during the externship.

Project breakdown

View all works