Kfir Toledo is an AI platform researcher at IBM Research Israel and a contributor to llm-d, vLLM, and the Gateway API Inference Extension. His work focuses on AI inference, AI networking, and multi-cloud systems, with a particular interest in making large-scale LLM inference affordable on commodity Kubernetes clusters. Before IBM, he worked at AWS. He holds B.Sc. and M.Sc. degrees from the Technion - Israel Institute of Technology.