I build AI systems that move beyond the prototype.
My work sits at the intersection of LLMs, agentic systems, retrieval, document intelligence, and backend engineering — turning research ideas into systems that can actually be evaluated, deployed, and used.
I'm currently working as an AI/ML Engineering Intern, building agentic research and report-generation systems alongside document-intelligence and LLM evaluation workflows.
My foundation is in full-stack engineering, which shapes how I approach AI: I think beyond the model itself — from data and retrieval → orchestration → APIs → infrastructure → user-facing products.
Agentic Systems · RAG / GraphRAG · Document Intelligence · LLM Evaluation
I build AI systems with a software-engineering mindset.
My experience spans agentic AI, LLM systems, document intelligence, evaluation, backend engineering, and cloud deployment — backed by a full-stack foundation that lets me work across the entire system rather than only the model layer.
The goal isn't just to make AI work. It's to make AI systems reliable enough to ship.
Engineering the layer between models and real-world systems.
I work across LLM applications, agentic workflows, retrieval, document intelligence, evaluation, and AI infrastructure — with an emphasis on systems that can be measured, integrated, and deployed.
A full-stack foundation for AI engineering.
I work across models → retrieval → orchestration → APIs → data → infrastructure → product, using the stack required to take an intelligent system from idea to deployment.
