Senior Software Engineer I - AI Inference Data Plane

Design, develop, and deliver high-scale, resilient data plane services for “Inference as a Service,” partnering across engineering and product to meet availability and performance goals. Lead end-to-end system design for a multi-tenant AI inference cloud, optimizing distributed serving with tensor/data parallelism, KV-cache strategies, and smart routing. Build Kubernetes-native inference frameworks, solve LLM-specific flow control and load balancing, contribute upstream, and mentor engineers while maintaining SLO-driven operations.