Projects
Projects from my research and engineering work, with enough detail to show what I built and how I tested it.
BioEvidence AI: Evidence-Grounded Biomedical Question Answering
A full-stack biomedical QA application with independently inspectable retrieval, reranking, generation, and citation-validation stages.
Retrieval, grounding, and evaluation work
Projects where evidence quality, system behavior, and inspection mattered as much as raw model output.
TREC BioGen: Evidence-grounded RAG and LLM evaluation system
Built and evaluated sparse and dense RAG pipelines over 26.8 million PubMed documents, with Qwen-based generation, reranking, and a dashboard for evidence-linked inspection.
Agentic and non-agentic multi-hop medical question answering
Compared an agentic evidence-search loop with controlled Wikipedia and Wikipedia + PubMed pipelines to study how tool use and retrieval strategy affect answer quality.
Insomnia classification and evidence extraction
Built baseline shared-task systems for identifying insomnia cases and extracting supporting evidence spans from clinical notes.
Biomedical negation detection with Transformers, CRF, and PPO
Fine-tuned BERT-family models for negation cue and scope tagging, then compared CRF, hierarchical, and PPO-based sequence-labeling approaches.
Product and platform work
Systems shaped by workflows, users, and constraints beyond a paper or benchmark.
Knowledge-Graph and Hybrid Retrieval for Course Enrollment
Built a Concordia course-enrollment knowledge base and natural-language QA system comparing graph, vector, and hybrid retrieval.
Government ID-based single sign-on authentication system (patent)
Proposed a single sign-on authentication workflow using government IDs, with a transparent QR-based verification process for secure identity validation.
Experiments and systems fundamentals
Smaller builds that still show how I think about modeling, performance, and implementation details.
Flight delay prediction system
Built a predictive ML engine to classify delayed flights and estimate delay duration, with preprocessing and model selection focused on operational reliability.
Dynamic branch predictor using deep learning
Team project on deep-learning-based dynamic branch prediction to reduce branching cost and improve processor pipeline execution behavior.