Ganesh Chandrasekar
I build retrieval, RAG, and language-model products where answers need to remain connected to their evidence.
Applied AI research shaped into usable product systems.
I am completing a Master of Computer Science thesis at Concordia University on evidence-grounded biomedical question answering. My work spans sparse and dense retrieval, open-source LLM inference, biomedical QA evaluation, and product-facing AI interfaces.
I care about systems that can be inspected: what they retrieved, what they answered, which evidence they used, and how a reviewer can trust the workflow.
BioEvidence AI began as a shared-task system and is becoming a live QA product.
For TREC BioGen 2025, I developed modular sparse and dense pipelines using BM25, Pyserini, MedCPT, cross-encoder reranking, TF-IDF/MMR, and Qwen. BioEvidence AI turns those evidence-grounded outputs into an inspectable product workflow.
Thanks to my collaborators, CLaC Lab, the TREC BioGen organizers, and the shared-task evaluators. Additional thesis systems will be added after defense and publication.