Projects
- Built a multi-tool LLM agent using MCP, integrating external medical APIs, a SQL-based patient database, and an Agentic RAG pipeline (FAISS + embeddings).
- Deployed a Streamlit-based UI with tool tracing, enabling transparent LLM decision-making.
- Implemented patient lookup, lab analysis, and risk scoring tools for clinical decision support workflows.
-
- Developed an agentic analytics system enabling natural language queries over structured Statistics Canada datasets.
- Integrated SQLite, ChromaDB, and Gemini to support retrieval-augmented reasoning and semantic search.
-
- Designed a multi-agent LLM chatbot for clinical diagnosis using LangChain-based orchestration.
- Implemented vector-based patient memory using Pinecone for context-aware medical conversations.
-
- Designed a Neural Collapse-inspired pruning framework to improve efficiency under data imbalance.
- Retained effective accuracy for minority classes during pruning.
- Achieved 95% accuracy up to 60% pruning.
-
- Built a MERN stack project management web app for university use.
- Implemented authentication with an admin portal for CRUD operations on projects.
- Developed RESTful APIs for creating, updating, and deleting project data.
-
