Your question is Design Edge Versus Cloud Inference. 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).
You are building a product that uses deep learning inference in both mobile or embedded environments and centralized backend services. The same user experience may need to work with intermittent connectivity, limited hardware, and stricter local constraints.
Explain the challenges of deploying deep learning models on edge devices versus cloud infrastructure.