Knowledge Graphs | Big Data | Agentic AI | Deep Learning
Building Neuro-symbolic AI systems that combine Knowledge Graphs with Large Language Models for explainable intelligence.
I completed my Ph.D. at the Artificial Intelligence Institute, University of South Carolina under Prof. Amit Sheth in the intersection of Knowledge Graphs (KGs) and Large Language Models (LLMs). My work focuses on building Neuro-symbolic frameworks that combine the reasoning capabilities of structured knowledge with the generative capabilities of LLMs and Agentic Systems for application- and user-level explainability in mission critical domains.
Previously, I led the development of EMPWR, the next-generation platform for managing the complete KG lifecycle: from design and ingestion to enrichment and maintenance at scale; also led the effort in developing Neuro-symbolic AI approaches to accelerate and automate medical device R&D, in collaboration with MedHive.ai.
I completed research internships at the National Library of Medicine (NLM) and Outreach.io, where I developed methods to create, manage, and maintain large-scale KGs for healthcare and sales intelligence applications.
Joined DataMinr as Research Scientist
Successfully defended my dissertation "A Neuro-Symbolic AI Framework for the Knowledge Graph Lifecycle" under Prof. Amit Sheth
Published "Toward Neurosymbolic Reinforcement Learning via Editable Specifications" in AAAI MAKE 2026
Ph.D. Proposal Defense: "A Neuro-Symbolic AI Framework for the Knowledge Graph Lifecycle" under Prof. Amit Sheth
Published "Building Multimodal Knowledge Graphs" in IEEE Internet Computing
Tutorial at KGSWC: "Data and Knowledge-Driven Processes for the Knowledge Graph Lifecycle"
U.S. Patent 12,067,983 issued for "Robust task-oriented virtual assistants"
IEEE Internet Computing
IEEE Internet Computing
U.S. Patent 12,067,983
The Web Conference (WWW)
IEEE Intelligent Systems
Interested in research collaborations, consulting opportunities, or discussing AI and knowledge graph projects? Let's connect.