Custom AI Development IDE & Agent Runtime
Architected an extensible AI development environment integrating Model Context Protocol (MCP) to orchestrate multi-step tool-calling workflows, backed by a scalable agent runtime on AWS EC2 and optimized edge SLM inference.
Oct 1, 2025
A Recommender System Architecture for University Curriculum Advising
This study proposes a goal-based agent recommender system for undergraduate students using a large language model, tailored to curriculum requirements, prerequisites, and student preferences. The system optimizes course selection, streamlines degree path exploration, and predicts enrollment metrics, reducing advisor workloads and promoting academic engagement, ultimately enhancing student success and increasing the overall academic achievement of the student body.
May 28, 2025
GraphRAG and Agentic Optimization for Student Curriculum Planning
30-minute research presentation on applying GraphRAG (Neo4j) and autonomous tool-calling agents to solve degree requirement planning for university students.
May 5, 2025
Agentic GraphRAG Recommender System
Published at AAAI 2025. Architected an autonomous multi-agent recommendation engine using GraphRAG (Neo4j) and dense vector retrieval (Qdrant) to resolve combinatorial degree requirements with human-in-the-loop verification.
Mar 25, 2025
A Recommender System Architecture for University Curriculum Advising
30-minute conference presentation introducing goal-based agent recommender systems for undergraduate curriculum advising at the AAAI Spring Symposium.
Mar 24, 2025
Automated Debug Assistant & Concurrency Scheduler OS
Implemented an automated LLM debugging assistant in C++ interfacing with Ollama REST APIs with mutex locks, deadlock prevention, and Dask distributed parallelization on Slurm HPC clusters.
Dec 1, 2023