FREE AI INTERVIEW QUESTIONS & ANSWERS
Prepare for AI engineer and Forward Deployed Engineer (FDE) interviews with free topic questions, matched source answers, foundation practice, and customer scenarios. All questions and answers are in English, with original source numbers preserved.
Explain the concept aloud, reveal the reference answer, and use the linked lab to try it yourself.
10 questions · Showing 1–10
Take the dot product of two nonzero vectors and divide by the product of their lengths. Validate matching dimensions and finite coordinates first.
Watch for: The formula is undefined when either vector has zero length.
For vectors normalized to unit length, their dot products equal their cosine similarities. Otherwise vector magnitude can change dot-product ranking.
Watch for: Do not normalize blindly if the embedding model expects a different scoring method.
No. It is a score under a particular representation and metric. Calibrate retrieval decisions with labeled tasks and verify answer claims separately.
Watch for: A high semantic match can retrieve an outdated or factually wrong passage.
Usually they must be regenerated or kept in separate compatible indexes. Equal vector lengths alone do not align the underlying spaces.
Watch for: Changing only the query model can silently damage retrieval.
Evaluate representative language, document types, queries, and relevance labels. Compare retrieval quality with latency, storage, and total processing cost.
Watch for: A larger dimension alone does not prove better results for your workload.
Metadata identifies the source, version, tenant or access scope, and other eligibility conditions. The vector alone cannot reliably encode those rules.
Watch for: Semantic similarity is not a permission check.
The global shortlist may contain only ineligible records. Filtering that truncated list cannot recover eligible records excluded before filtering.
Watch for: An empty shortlist does not prove the eligible corpus contains no answer.
Exact search considers the full eligible set under the defined metric. Approximate search trades some retrieval accuracy for efficiency through an index or candidate-selection method.
Watch for: This three-record sorting example is not evidence of approximate-index performance.
Associate chunks with a document version, publish a consistent updated set, and remove or exclude superseded chunks. Test retrieval immediately after the change.
Watch for: Adding new vectors while keeping old conflicting passages active can mix policy versions.
Measure recall against an exact baseline together with latency, memory, build time, updates, and filtering behavior on representative data.
Watch for: A latency number without corpus size and recall conditions is hard to interpret.
