Your question is Designing a Highly Available API. 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 design a highly available API that handles millions of requests per day?
Treat this as a production ML inference API. Explain how you would clarify requirements, estimate capacity, design the online and offline paths, and preserve availability when dependencies or models fail.
Address the API contract, multi-region architecture, model serving, caching, autoscaling, observability, deployment strategy, security, and offline and online evaluation.