Amazon Web Services AI Engineer Interview Questions

The questions to prepare for a Amazon Web Services AI Engineer interview. Questions from real interview reports rank first. Updated daily.

36questions

~5htotal time

Track your progressSign up free to work through all 36 questions and resume where you left off.

System DesignStart here. 8 questions · ~73 min

Design how to present, scale, and monitor AGI projects from a resume, including architecture choices and failure handling.

Resource-Constrained System DesignHard

Design how an ML system changes when compute, data, and serving budget are cut to 20%.

production deploymentFeature Storeinference latency

Amazon Web Services

More System Design questions with a free account

Coding8 questions · ~73 min

Evaluates your coding fundamentals and ability to implement correct game logic.

Top-K Similarity Index for EmbeddingsHard

Practice

Maintain the top-k cosine-similar embeddings from a stream using normalization and a bounded min-heap.

Amazon Web Services

More Coding questions with a free account

Create a free account to unlock this list and practice real interview questions.

Generative AI & LLMs9 questions · ~82 min

Single vs Multi Agent SupportEasy

Compare single-agent and multi-agent designs for customer support, with attention to evaluation, safety, latency, and operational tradeoffs.

Amazon Web Services

Design a Multi-Tool AI AgentHard

Design a production agent platform that coordinates models, tools, and data sources under strict latency, cost, and safety limits.

Vector SearchPrompt EngineeringRAG

Amazon Web Services

More Generative AI & LLMs questions with a free account

NLP3 questions · ~27 min

Embedding Distortion and HNSW TuningMedium

Tests understanding of vector search behavior and practical tuning of HNSW for recall-speed trade-offs.

Vector Search

Amazon Web Services