RAG Systems · Machine Learning · Deep Learning · NLP
I'm an AI Engineer and graduate researcher at SUNY Polytechnic Institute — I don't just build models, I engineer production AI systems that scale.
My focus: Retrieval-Augmented Generation, Graph RAG architectures, LLM fine-tuning, and end-to-end ML pipelines. I take research from prototype to deployment — FastAPI services, vector databases, real-time inference.
Fluent across the full AI stack: PyTorch, TensorFlow, LangChain, LlamaIndex, HuggingFace Transformers, and cloud ML platforms. I build systems that are fast, reliable, and measurably correct.
From research to production — I engineer the full AI stack: model architecture, fine-tuning, vector retrieval, API deployment, and cloud-scale inference. Every layer, end to end.
End-to-end AI data platform combining RAG pipelines, modular vector search, and real-time analytics dashboards. Designed for production-scale deployment — live on Streamlit.
Conversational AI with semantic FAISS retrieval, context-aware multi-turn memory, and document Q&A. Built end-to-end with LangChain — production-deployed on Streamlit.
ML-powered predictive pricing, geospatial market clustering, and trend forecasting — all in one interactive Plotly dashboard. Built with Scikit-learn and deployed live on Streamlit.
Building production RAG and Graph RAG systems for active research. Designing synthetic data pipelines, collaborating on NLP and semantic search projects, and developing scalable LLM architectures.
Research and coursework in RAG systems, embeddings, and scalable ML pipelines. Focus on applied deep learning and statistical modeling.
End-to-end data services across 2 years — cleaning, processing, validation, and dashboard development. Built Tableau and Power BI dashboards. Used Python and SPSS to identify market trends that drove business decisions.
Postgraduate program in software engineering, algorithms, and applied computing. Foundation in data structures and software architecture.