Welcome to your interview.
The question is on your right: Design a Fault-Tolerant Web ML Stack. Take a moment with it first.
Talk your thinking through with me if you like - when you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes). Discussion and graded submissions share your five interviewer interactions, so spend them well.
You are building a web application that relies on machine learning for core user-facing decisions. The product must stay usable during infrastructure failures, degraded dependencies, and bad model rollouts, while still serving predictions with acceptable quality.
What approaches do you take to ensure high availability and fault tolerance in a web application?