AI Engineer • Behavioral • hard

Describe an AI product you built from scratch. What were the key technical decisions?

#Product Development

Practice

AI Engineer • Behavioral • hard

Tell me about a time an AI system you built produced unexpected or harmful outputs.

#Responsibility #Ethics

Practice

AI Engineer • Behavioral • easy

How do you stay current with the fast-moving AI/ML research landscape?

#Research #Continuous Learning

Practice

AI Engineer • Behavioral • medium

Describe a time you had to choose between using an AI model and a simpler rule-based system.

#Tradeoffs #Pragmatism

Practice

AI Engineer • Behavioral • medium

Tell me about a time you optimized an LLM application for cost or latency.

#Cost #Latency

Practice

AI Engineer • Behavioral • medium

How do you handle stakeholder uncertainty around AI capabilities and limitations?

#Stakeholders #Expectations

Practice

AI Engineer • Behavioral • hard

Describe a situation where you had to debug a hard-to-reproduce AI model failure.

#Problem Solving

Practice

AI Engineer • Behavioral • hard

Tell me about an AI project where you had to balance innovation with reliability.

#Reliability #Innovation

Practice

AI Engineer • Coding • hard

Implement a simple RAG pipeline using Python, LangChain, and FAISS.

#RAG #Python

Practice

AI Engineer • Coding • medium

Write a Python class to manage conversation history for a multi-turn chatbot.

#Chatbot #Memory

Practice

AI Engineer • Coding • hard

Implement a semantic chunking strategy for long documents.

#Chunking #Embeddings

Practice

AI Engineer • Coding • medium

Write a retry mechanism with exponential backoff for LLM API calls.

#Reliability #APIs

Practice

AI Engineer • System Design • hard

Design an AI-powered customer support chatbot for an e-commerce platform.

#Chatbot #LLM

Practice

AI Engineer • System Design • hard

Design a document question-answering system using RAG.

#RAG #Vector Search

Practice

AI Engineer • System Design • hard

Design an AI code review system that integrates with GitHub PRs.

#Code Review #LLM

Practice

AI Engineer • System Design • hard

How would you build a multi-modal AI system that processes both text and images?

#Multi-Modal #Vision

Practice

AI Engineer • System Design • hard

Design a real-time AI safety filter for user-generated content.

#Content Moderation #Real-Time

Practice

AI Engineer • System Design • hard

How would you architect an AI platform that supports 1000 concurrent LLM requests?

#Scaling #LLM Serving

Practice

AI Engineer • System Design • hard

Design an AI agent system that can autonomously browse the web and complete tasks.

#Agents #Tool Use

Practice

AI Engineer • Technical • hard

Explain the difference between GPT, BERT, and T5 architectures.

#GPT #BERT #T5

Practice

AI Engineer • Technical • medium

What is prompt engineering? What are few-shot, zero-shot, and chain-of-thought prompting?

#Prompt Engineering #Few-Shot

Practice

AI Engineer • Technical • hard

Explain how RLHF (Reinforcement Learning from Human Feedback) improves LLMs.

#RLHF #Alignment

Practice

AI Engineer • Technical • hard

What is RAG (Retrieval-Augmented Generation)? When would you use it over fine-tuning?

#RAG #Fine-Tuning

Practice

AI Engineer • Technical • medium

Explain the difference between fine-tuning and in-context learning.

#Fine-Tuning #ICL

Practice

AI Engineer • Technical • medium

What is token context window? How do you handle documents longer than the context limit?

#Context Window #Chunking

Practice

AI Engineer • Technical • hard

Explain positional encoding in transformers. What are the differences between absolute and rotary position embeddings?

#Positional Encoding #RoPE

Practice

AI Engineer • Technical • hard

What is hallucination in LLMs? How do you detect and mitigate it?

#Hallucination #Safety

Practice

AI Engineer • Technical • medium

Explain the difference between autoregressive and masked language modeling.

#Autoregressive #Masked LM

Practice

AI Engineer • Technical • hard

What is a mixture of experts (MoE) architecture? How does it scale?

#MoE #Scaling

Practice

AI Engineer • Technical • hard

Explain how vector similarity search works. What are HNSW and IVF indices?

#HNSW #Similarity Search

Practice

AI Engineer • Technical • medium

Compare vector databases: Pinecone, Weaviate, Qdrant, and pgvector.

#Vector DB #Embeddings

Practice

AI Engineer • Technical • medium

How do you choose the right embedding model for a domain-specific search task?

#Embedding Models #Search

Practice

AI Engineer • Technical • medium

What is semantic search? How does it differ from keyword-based search?

#Semantic Search #NLP

Practice

AI Engineer • Technical • hard

Explain the difference between dense and sparse retrieval in RAG.

#Dense Retrieval #BM25

Practice

AI Engineer • Technical • hard

How do you evaluate retrieval quality in a RAG system?

#Evaluation #Retrieval

Practice

AI Engineer • Technical • hard

How do you evaluate the quality of an LLM-generated response?

#LLM Evaluation #RAGAS

Practice

AI Engineer • Technical • hard

What is AI alignment? What are the key safety concerns with large-scale AI deployment?

#Alignment #Safety

Practice

AI Engineer • Technical • hard

Explain the concept of AI bias. How do you detect and mitigate it in production?

#Bias #Fairness

Practice

AI Engineer • Technical • hard

What is Constitutional AI? How does Anthropic use it?

#Constitutional AI #Anthropic

Practice

AI Engineer • Technical • hard

How do you red-team an AI system?

#Red Teaming #Security

Practice

AI Engineer • Technical • medium

What are guardrails in LLM applications? How do they work?

#Guardrails #Output Filtering

Practice

AI Engineer • Technical • medium

How do you integrate OpenAI API or Gemini API into a production application?

#OpenAI #Gemini

Practice

AI Engineer • Technical • medium

What is LangChain? What are its key components (Chains, Agents, Tools)?

#LangChain #Agents

Practice

AI Engineer • Technical • hard

Explain function calling / tool use in LLMs. How do you implement it?

#Function Calling #Tool Use

Practice

AI Engineer • Technical • medium

How do you manage LLM API rate limits and costs in production?

#Rate Limiting #Cost

Practice

AI Engineer • Technical • medium

What is streaming response from an LLM API? How do you implement it in a web app?

#Streaming #API

Practice

AI Engineer • Technical • medium

Explain structured output generation from LLMs (JSON mode, Instructor library).

#Structured Output #JSON

Practice

Meta

The Interview Loop

Recruiter Screen (30 min)

Technical Loop (3-4 Rounds)

Interview Question Bank

Describe an AI product you built from scratch. What were the key technical decisions?

Tell me about a time an AI system you built produced unexpected or harmful outputs.

How do you stay current with the fast-moving AI/ML research landscape?

Describe a time you had to choose between using an AI model and a simpler rule-based system.

Tell me about a time you optimized an LLM application for cost or latency.

How do you handle stakeholder uncertainty around AI capabilities and limitations?

Describe a situation where you had to debug a hard-to-reproduce AI model failure.

Tell me about an AI project where you had to balance innovation with reliability.

Implement a simple RAG pipeline using Python, LangChain, and FAISS.

Write a Python class to manage conversation history for a multi-turn chatbot.

Implement a semantic chunking strategy for long documents.

Write a retry mechanism with exponential backoff for LLM API calls.

Design an AI-powered customer support chatbot for an e-commerce platform.

Design a document question-answering system using RAG.

Design an AI code review system that integrates with GitHub PRs.

How would you build a multi-modal AI system that processes both text and images?

Design a real-time AI safety filter for user-generated content.

How would you architect an AI platform that supports 1000 concurrent LLM requests?

Design an AI agent system that can autonomously browse the web and complete tasks.

Explain the difference between GPT, BERT, and T5 architectures.

What is prompt engineering? What are few-shot, zero-shot, and chain-of-thought prompting?

Explain how RLHF (Reinforcement Learning from Human Feedback) improves LLMs.

What is RAG (Retrieval-Augmented Generation)? When would you use it over fine-tuning?

Explain the difference between fine-tuning and in-context learning.

What is token context window? How do you handle documents longer than the context limit?

Explain positional encoding in transformers. What are the differences between absolute and rotary position embeddings?

What is hallucination in LLMs? How do you detect and mitigate it?

Explain the difference between autoregressive and masked language modeling.

What is a mixture of experts (MoE) architecture? How does it scale?

Explain how vector similarity search works. What are HNSW and IVF indices?

Compare vector databases: Pinecone, Weaviate, Qdrant, and pgvector.

How do you choose the right embedding model for a domain-specific search task?

What is semantic search? How does it differ from keyword-based search?

Explain the difference between dense and sparse retrieval in RAG.

How do you evaluate retrieval quality in a RAG system?

How do you evaluate the quality of an LLM-generated response?

What is AI alignment? What are the key safety concerns with large-scale AI deployment?

Explain the concept of AI bias. How do you detect and mitigate it in production?

What is Constitutional AI? How does Anthropic use it?

How do you red-team an AI system?

What are guardrails in LLM applications? How do they work?

How do you integrate OpenAI API or Gemini API into a production application?

What is LangChain? What are its key components (Chains, Agents, Tools)?

Explain function calling / tool use in LLMs. How do you implement it?

How do you manage LLM API rate limits and costs in production?

What is streaming response from an LLM API? How do you implement it in a web app?

Explain structured output generation from LLMs (JSON mode, Instructor library).

Difficulty Radar

Meet Your Interviewers

The "Standard" Interviewer

Unwritten Rules