Senior Software Engineer I - AI Inference Data Plane

Design and deliver high-scale, resilient AI inference data plane services that power “Inference as a Service.” Lead end-to-end architecture and implementation for a multi-tenant, Kubernetes-native serving stack, optimizing distributed inference performance with KV-cache strategies, tensor/data parallelism, and intelligent routing/load balancing. Contribute upstream to key inference projects and mentor engineers while maintaining reliability through observability and SLOs.