I’m an AI Engineer focused on building production-ready intelligent systems that solve real-world problems. My work spans large language model (LLM) applications, retrieval-augmented generation (RAG), and AI agent workflows, where I design systems that are measurable, reliable, and scalable.

I have hands-on experience developing end-to-end AI pipelines—from data ingestion and retrieval optimization to prompt engineering, structured outputs, and evaluation frameworks. I actively work on improving model performance through techniques like reranking, prompt iteration, and response evaluation, with a strong focus on delivering grounded and high-quality outputs in real-world scenarios.

Beyond AI, I bring strong full-stack engineering capabilities. I’ve built and deployed systems using Node.js, React, MongoDB, and FastAPI, and I’m comfortable working across backend infrastructure, APIs, and real-time communication systems. My experience also includes working with vector databases, REST architectures, and production-grade deployment workflows.

I’m particularly interested in building AI systems that directly impact business workflows—automation, decision support, and intelligent user interfaces—rather than experimental prototypes. I value clean architecture, observability, and continuous evaluation when shipping AI systems.

Whether it’s designing LLM-powered applications, building scalable backend systems, or integrating AI into real-world products, I focus on creating systems that are practical, efficient, and built to last.