Your question is Distributed Evaluation at Scale Across Clouds. 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 would you architect a distributed model evaluation system that can run inference on billions of image frames across multiple cloud providers (AWS and GCP) while minimizing data egress costs for Encord?