Specializing in LLM agents, RAG pipelines, and production ML systems. From research to deployment, I architect scalable AI solutions that solve real-world problems.
I architect and deploy production-grade AI systems with a focus on LLM agents, RAG pipelines, and agentic architectures. My work spans from research to production deployment, with expertise in GCP, AWS, and modern ML frameworks.
Currently building the future of AI chatbots through MCP (Model Context Protocol) and Arazzo, while maintaining production systems that process millions of queries with high accuracy and low latency.