Pfizer logoPfizer Externship via Extern
Abdulrahman Z. portrait

Third-year software engineering student focused on AI and data extraction

I build and test AI-driven approaches for extracting insights from documents, blending coursework with hands-on externship experience.

Work samples

Work samples show experiments and deliverables from coursework and the Pfizer externship, focused on document parsing, data extraction, and AI-assisted insight generation.

  • Aphasia Bridge
    Aphasia Bridge

    Built and stress-tested a Python word-prediction model, achieving 99.6% accuracy across 2,150 trials and 97.9% accuracy with 30% incorrect inputs; Connected a React Native app to speech-to-text and AI sentence reconstruction, transforming fragmented speech into complete sentences spoken aloud; Defined the Flask REST API contract, enabling a 5-engineer team to ship a 4-screen application in 48 hours with no integration conflicts

    React NativeFlaskWhisperClaude API
  • Multi-Tenant File Sharing App
    Multi-Tenant File Sharing App

    Built a FastAPI + PostgreSQL multi-tenant file API with JWT authentication, RBAC, and tenant-scoped isolation; Implemented quota-checked uploads, tokenized share links, and audit logging behind a swappable storage backend; Shipped a Docker Compose deployment validated by 27 automated API tests built with pytest, covering REST API authentication, tenancy, uploads, and share downloads to ensure regression-safe releases

    PythonFastAPIPostgreSQLDocker

About me

I build and test AI-driven approaches for extracting insights from documents, blending coursework with hands-on externship experience.

I am Abdulrahman Z., a third-year software engineering student working toward a bachelor's degree. I have some practical experience and completed the Pfizer Advanced: AI-Powered Document Insights & Data Extraction externship, where I worked on AI and data extraction concepts relevant to document processing.

Externships

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

In progress

Experience

AI Automation Developer

Mitacs × Canadian Furniture Group · May 2026 – Present

Backend Developer

Kimuntu Power Inc. · Jun 2026 – Jul 2026

Programming and Data Management Teaching Assistant

Carleton University · May 2026 – Jun 2026

Undergraduate AI/ML Research Assistant

Carleton University · Mar 2026 – May 2026

Education

Carleton University

Bachelor of Software Engineering (Co-op), cGPA: 3.83/4.0 | Dean’s List: 2024–2026

Skills

AI for document processingData extractionSoftware engineering fundamentalsModel experimentationPrototype implementation

Aphasia Bridge

Built and stress-tested a Python word-prediction model, achieving 99.6% accuracy across 2,150 trials and 97.9% accuracy with 30% incorrect inputs; Connected a React Native app to speech-to-text and AI sentence reconstruction, transforming fragmented speech into complete sentences spoken aloud; Defined the Flask REST API contract, enabling a 5-engineer team to ship a 4-screen application in 48 hours with no integration conflicts

React NativeFlaskWhisperClaude API
View all work

Multi-Tenant File Sharing App

Built a FastAPI + PostgreSQL multi-tenant file API with JWT authentication, RBAC, and tenant-scoped isolation; Implemented quota-checked uploads, tokenized share links, and audit logging behind a swappable storage backend; Shipped a Docker Compose deployment validated by 27 automated API tests built with pytest, covering REST API authentication, tenancy, uploads, and share downloads to ensure regression-safe releases

PythonFastAPIPostgreSQLDocker
View all work

✅ 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 prototyped AI-powered document intelligence for enterprise PDF workflows. Work combined OCR, large language models, and retrieval-augmented generation to extract structured data and surface document insights. Deliverables included research artifacts, prototypes, and documented findings from model experiments.

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

What I've accomplished

I documented how a large language model is trained to predict next tokens, explained that it composes plausible-seeming text without human-like understanding, and recorded that it can produce incorrect but confident answers when applied to pharmaceutical documents.

Project breakdown

I described how an LLM was trained on massive text to predict the next word, how it composes plausible-seeming output without human-like understanding, and noted it can produce incorrect but confident answers.

View all work