Your question is Kubernetes Autoscaling. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
How do you handle autoscaling in Kubernetes?
Asked in the Technical Round 1 stage. Explain how you would autoscale a Kubernetes-based ML inference system, including workload signals, scaling layers, latency protection, and failure handling. Address both practical configuration choices and how you would validate that scaling improves reliability without causing instability or excessive cost.