Your question is Scalable API Under Constraints. 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).
Describe how you would design a scaling API application given specific constraints.
Focus on how you would size the system, choose the serving architecture, and handle latency, cost, and reliability tradeoffs. Assume the API must support both online requests and offline learning or optimization loops, with clear monitoring and fallback behavior.