What is an embedding, and how would you use embeddings in a product feature?

What the interviewer wants to hear

• A dense vector representation learned so similar items are close
• Similarity is measured with cosine or dot product
• Used for semantic search, recommendations, clustering and RAG
• Stored in a vector index for fast nearest-neighbour search
• Quality should be checked on your own data

Model answer

An embedding is a list of numbers, a dense vector, that a model produces for a piece of text, an image, a user or a product. The model is trained so that things with similar meaning or behaviour end up close together in that space. I usually compare embeddings with cosine similarity. In a product, a common use is semantic search: embed every help article once, store the vectors in a vector index, then embed the user query and return the nearest articles, even when they share no exact words. The same idea powers related-item recommendations, duplicate detection, clustering of support tickets and retrieval for RAG. Before shipping I test the embedding model on real queries from our domain, because a general model can miss jargon, and I often add keyword search for exact codes.

More easy Machine Learning Engineer questions

• What is overfitting, how do you detect it, and how do you reduce it?
• Explain precision and recall with a real example. When would you favour one over the other?
• How does gradient descent work, and what is the role of the learning rate?
• What are the training, validation and test sets used for, and how do you split them?
• Why should you build a simple baseline before a complex model? Give examples of good baselines.
• Explain the bias-variance trade-off and how it guides your choice of model.
• When would you choose a tree-based model like gradient boosting over a linear model, and when not?
• How do you handle missing values in a dataset before training a model?
• Explain in simple terms how self-attention works in a transformer.