Whenever you're ready, walk me through how you'd approach this.
Tell me about a machine learning project you worked on in the last two years, including the system design and what you learned.
Choose a project where you can explain the problem, data flow, model architecture, training and serving paths, evaluation, and your individual contributions. Be prepared to discuss scale, latency, cost, model or feature changes, production failures, monitoring, and how the system evolved. If your project used multiple prediction stages, explain retrieval, ranking, and re-ranking decisions.