AI Application Engineer · AI Agent · Web3
Hello.
I'm Jemy Yan, an AI application engineer based in China. I build intelligent systems powered by LLMs and AI agents — from RAG applications and autonomous agents to Web3 dApps and full-stack AI products. I leverage Claude, GPT, and modern AI development tools to ship end-to-end solutions from architecture to production.
With deep experience in AI integration, prompt engineering, and full-stack development, I turn AI capabilities into real-world applications. I'm passionate about how AI agents and LLMs are transforming software development and creating new possibilities for intelligent automation.
I specialize in building production-grade AI applications — from RAG systems and AI agents to LLM-powered products and intelligent automation. My work spans the full stack: API integration, prompt engineering, vector databases, agent orchestration, and user-facing interfaces. I bring both technical depth and product thinking to turn AI capabilities into reliable, scalable solutions that solve real problems.
I've built AI-powered applications across multiple domains — intelligent agents, RAG systems, LLM-powered tools, Web3 dApps, and full-stack platforms. From prototyping to production deployment, I deliver complete solutions that integrate AI capabilities with robust engineering practices.
I'd love to hear from you — whether it's about a project, a collaboration, or just to say hello.