I design and build intelligent AI systems that deliver real impact — from RAG architectures to LLM pipelines and scalable data solutions.
I'm a Data Science and Analytics graduate student at SUNY Polytechnic Institute, specializing in building intelligent AI systems that bridge research and production. My core focus areas are Retrieval-Augmented Generation (RAG), Graph RAG architectures, LLM fine-tuning, and scalable ML pipelines.
With hands-on expertise in Python, TensorFlow, PyTorch, LangChain, and modern AI frameworks, I build production-grade systems that go beyond prototypes — from real-time data pipelines to multi-hop reasoning engines powered by knowledge graphs.
My approach combines rigorous technical depth with practical engineering — whether architecting a cardiovascular risk prediction model with explainability or deploying a Graph RAG system for multi-document reasoning.
Building cutting-edge RAG systems, Graph RAG with Neo4j, LLM fine-tuning, and intelligent information retrieval architectures.
End-to-end ML pipelines, predictive modeling, statistical analysis, and production-grade deployments with 90%+ accuracy.
Scalable backend systems with FastAPI, real-time streaming pipelines, vector databases, and cloud-native deployments.
Developing and implementing RAG systems and ML infrastructure to support research and applied AI projects. Focus on Graph RAG architectures, LLM fine-tuning, and synthetic data generation pipelines.
Led data analytics initiatives including statistical analysis, dashboard generation, and data-driven solutions to support operational and business decisions.
Research & coursework centered on RAG systems, embeddings, LLM architectures, and scalable ML pipelines.
Software engineering, algorithms, and applied computing. Strong foundation in programming and analytical thinking.
Production-grade AI systems, ML platforms & data solutions
ML platform for cardiovascular disease risk prediction using hybrid ensemble models, deep learning, and SHAP-powered explainability.
Graph RAG implementation using LightRAG for multi-hop reasoning. Neo4j knowledge graphs for improved contextual understanding across documents.
Unified Streamlit dashboard integrating 7 analytical projects — COVID-19 tracking to restaurant analytics — using live APIs and rich datasets.
Real-time logistics data streaming and analytics pipeline with live monitoring dashboard. Event-driven architecture with real-time insights.
Multi-domain analytical dashboard covering world university rankings, COVID-19 tracking, restaurant analytics, and more with interactive visualizations.
Have a project in mind, a research idea, or want to collaborate? I'd love to hear from you.