Your question is Debugging Latency Spikes. 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).
If your model's latency spikes in production at Netflix, what is your systematic approach to debugging the bottleneck?
Explain how you would distinguish model, feature, infrastructure, dependency, and traffic causes. Cover observability, controlled experiments, mitigation, capacity planning, and prevention of recurrence.