Senior Engineer, Inference Data Plane

Design and deliver high-scale, resilient AI inference data plane services for “Inference as a Service.” Lead end-to-end system design for a multi-tenant inference cloud, optimize distributed serving performance (tensor/data parallelism, KV-cache techniques, routing, caching), and build Kubernetes-native inference frameworks. Collaborate with product and engineering teams, contribute upstream to projects like llm-d and vLLM, mentor junior engineers, and maintain SLO-driven operational excellence.