I’m an AI engineer and cloud architect with 14+ years of experience building and scaling real-world software systems. I help startups and product teams turn LLM ideas into production-ready AI applications, combining LangChain/LangGraph, Java, Python, TypeScript, and cloud-native architecture to deliver reliable, scalable results—not just demos.
I specialize in developing end-to-end AI systems, including LLM-powered APIs, RAG pipelines, backend services, and event-driven microservices. With extensive hands-on experience in Docker, Kubernetes, Azure, CI/CD, and Kafka, I design AI platforms that are secure, observable, cost-efficient, and built to scale from the outset.
Currently working at Microsoft, I bring enterprise-grade engineering discipline to fast-moving startup environments. I work comfortably in small, distributed teams, communicate clearly with technical and non-technical stakeholders, and focus on shipping AI features that directly impact users and business outcomes.