/* I work across machine learning, GIS, and document intelligence, turning messy data into structured, useful outputs through Python, spatial analysis, and applied AI. */
🟢 Open to work
Currently an Extern @PfizerPortfolio items focus on AI approaches to extract data from documents, improve parsing accuracy, and produce structured outputs from unstructured sources.
.jpg)
✅ Verified by Extern
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 work across machine learning, GIS, and document intelligence, turning messy data into structured, useful outputs through Python, spatial analysis, and applied AI.
I’m a Computing and GIS student and University of Toronto Geography graduate building skills across software, geospatial technology, machine learning, and data. My experience includes Python, spatial analysis, data analytics, and applied AI, with a growing focus on software engineering and building practical, data-driven solutions.
Externships
Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
Pfizer
Experience
Machine Learning Engineer Intern
FlyRank AI · Aug 2026
Pfizer — Advanced AI-Powered Document Insights & Data Extraction Extern
EXTERN · Aug 2026
Safe Staffing Agency
Safe Staffing Agency · Oct 2025 - Jun 2026
Data Analyst Intern
Ada Analytics · Jan 2022 - Apr 2022
Research Assistant
Antarctic Institute of Canada · Jan 2022 - Apr 2022
Education
Thompson Rivers University (TRU)
Bachelor of Computing Science (BCS) · Class of 2029
Centre of Geographic Sciences (COGS)
Graduate Certificate in Geographic Information Systems (GIS) · Class of 2027
University of Toronto
Honours Bachelor of Arts · Class of 2026
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 language models. The work surveyed LLM fundamentals, designed extraction flows, and produced prototype artifacts for automated data extraction and document summarization.
I documented how LLMs are trained on large text corpora and how they generate token-by-token responses based on context rather than retrieving prewritten answers.
I explained that LLMs were trained on vast text corpora, learned word and sentence patterns by predicting next tokens, and generate new responses token by token using context rather than retrieving prewritten answers.
