Stephen Koo

Senior Software Engineer with 8+ years of experience building scalable backend systems, AI infrastructure, and production LLM platforms. Expertise in distributed systems, Kubernetes-based ML serving, retrieval-augmented generation (RAG), and generative AI integration using Vertex AI and Gemini. Proven track record delivering high-availability AI services supporting millions of users across global cloud environments.

Core Skills: LLM Infrastructure • AI Inference Systems • Distributed Systems • Kubernetes • RAG • Vertex AI • Scalable Backend Systems • ML Platform Engineering