A media company operates a video rendering pipeline on Amazon EKS, where containerized jobs are scheduled using Kubernetes deployments. The application experiences bursty traffic patterns, particularly during peak streaming hours. The platform uses the Kubernetes Horizontal Pod Autoscaler (HPA) to scale pods based on CPU utilization. A solutions architect observes that the total number of EC2 worker nodes remains constant during traffic spikes, even when all nodes are at maximum resource utilization. The company needs a solution that enables automatic scaling of the underlying compute infrastructure when pod demand exceeds cluster capacity. Which solution should the architect implement to resolve this issue with the least operational overhead?