Your question is Embeddings and Vector Search. 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).
What techniques would you use for embeddings and vector search in a recommendation system at New York Life?
Explain how you would represent users, products, and natural-language content; select and train an embedding model; build an efficient nearest-neighbor index; and combine semantic similarity with recommendation signals. Discuss preprocessing, cold-start handling, retrieval quality, latency, and how you would evaluate the system.