Design, develop, test, and maintain features for the GKE Agent Gateway, enhancing its capabilities for AI/ML workloads and Contribute to the GKE Gateway controller OSS community as a lead on Inference.
Collaborate with Load Balancing development teams on requirements and integrations with Google Cloud Load Balancers (e.g., Envoy features and Service Extensions).
Engage with and contribute to the upstream OSS Kubernetes Gateway API project.
Work with AI/ML platform teams to ensure optimal routing, load balancing, and autoscaling for inference serving.
Develop solutions that span both the Kubernetes control plane and the load balancing data plane and constantly work on improving observability, testability, and reliability of the Inference Gateway.

Staff Software Engineer, Load Balancing and Agent Gateway

Job Description