
Applied Math & Computer Engineering
Queen's University
I focus on computer science, real analysis, probability theory, control systems, and stochastic calculus. My goal is to build intelligent systems that bridge the gap between theory and application.
Developed and deployed Azure-based workflows to transcribe, classify, and organize refugee basis-of-claim documents with 93% accuracy, significantly reducing manual processing time. Built an Azure chatbot using Cosmos DB, NLP, and embedding pipelines to cut legal document ingestion to under 10 minutes and presented the system’s impact to stakeholders at a conference.
Conducted AI research in a 12-week program under mentorship from PhDs at Meta, OpenAI, and Princeton. Improved large language model efficiency by implementing a self-contrastive Mixture-of-Experts architecture in PyTorch and co-authoring a paper under review introducing contrastive decoding methods with a 2% benchmarked efficiency gain.