With extensive experience building large, scalable applications from the ground up, I specialize in full-stack development, DevOps, and cloud infrastructure (AWS). I’ve designed and deployed production-grade systems using microservices, Docker, and Kubernetes, and have led end-to-end delivery—from architecture to cloud deployment. Over the past few years, I’ve increasingly focused on AI-native development, working with generative AI, agentic systems, and retrieval-augmented generation (RAG) pipelines. I’ve built intelligent applications using LangGraph, LangChain, and vector databases like Weaviate and Pinecone, integrating LLMs into real-world workflows. My work spans glue-code engineering, agent orchestration, and fast prototyping of AI-powered tools. Driven by a strong product mindset, I thrive in small teams where I can ship fast, iterate quickly, and build meaningful, intelligent systems that scale.
