Interview kits

AI-GenAI Engineer

1,027 interview questions for AI and GenAI engineers, answered

• Answer the math, ML and deep learning fundamentals interviewers still ask
• Explain transformers and LLMs from attention to decoding
• Apply prompt engineering and choose when to fine-tune
• Build GenAI backends with FastAPI and deploy them
• and 4 more

For AI, ML and GenAI engineers, LLM engineers, agent developers, and software engineers moving into AI roles.

AI Agents

610 interview questions on building, shipping and defending AI agents, answered

• Explain agent architectures, from reactive loops to planner-executor designs
• Compare the major agent frameworks and say when to use each
• Design tool calling, memory and reflection for a real agent
• Take an agent to production with evaluation, observability and cost control
• and 3 more

For AI, ML and LLM engineers, GenAI developers, and students preparing for AI system design interviews.

AI System Design

380 interview questions on designing AI systems at scale, answered

• Structure an AI system design interview answer from requirements to trade-offs
• Design LLM, RAG and agent systems for latency, cost and reliability
• Scale AI systems in production and explain where they fail
• Design inference and serving infrastructure, including caching and batching
• and 3 more

For AI and ML engineers, backend engineers transitioning to AI, and anyone who has to design and scale AI systems in production.

LLMOps

370 interview questions on running LLM systems in production, answered

• Explain the LLM lifecycle and what LLMOps adds to MLOps
• Run prompt, model and RAG experiments with proper tracking
• Deploy and scale LLM inference infrastructure
• Monitor, evaluate and observe LLM systems in production
• and 4 more

For ML engineers, backend and platform engineers, data scientists and AI architects preparing for LLMOps and AI engineering roles.

MLOps Engineer (Classical)

625 interview questions for MLOps engineers, answered

• Explain why MLOps exists and what it adds to DevOps
• Build data pipelines and track experiments and models
• Test ML systems and automate CI/CD and continuous training
• Serve models and monitor them for drift and failures
• and 4 more

For Engineers preparing for a first MLOps role, ML engineers moving into MLOps, platform engineers, and seniors preparing for staff-level interviews.

DSA for AI Engineers

236 coding interview questions for AI engineers, answered

• Recognize the core DSA patterns and when each one applies
• Solve coding problems in Python and explain the complexity
• Reason about time and space trade-offs out loud
• Apply DSA to AI tasks such as tokenization, batching and retrieval
• and 2 more

For AI and ML engineers, data scientists moving into ML roles, students preparing for AI technical interviews, and engineers moving into GenAI systems.

AI Security

596 interview questions on securing AI systems, answered

• Threat-model LLM, RAG and agent systems end to end
• Explain prompt injection, data exfiltration and jailbreak techniques
• Design layered defenses and guardrails for production AI
• Secure agents, tools and protocols such as MCP
• and 4 more

For AI and ML engineers, data scientists, backend engineers, and anyone responsible for securing and deploying AI in production.

AI Product Manager

376 interview questions for product managers building AI products, answered

• Decide when a problem needs AI and when it does not
• Define success metrics and guardrails for an AI product
• Build a credible AI roadmap and defend it to stakeholders
• Work fluently with ML teams on data, models and evaluation
• and 4 more

For Product managers moving into AI, engineers and data scientists moving into PM roles, and senior leaders targeting advanced positions.

RAG

405 interview questions on retrieval-augmented generation, answered

• Explain each RAG component and how its choices affect quality
• Choose chunking, embedding and vector database strategies
• Design retrieval, reranking and generation for grounded answers
• Evaluate a RAG system and find where it fails
• and 3 more

Healthcare RAG and Agents

250 interview questions on building RAG and agents for healthcare, answered

• Explain where RAG and agents add value in healthcare, and where they must not act alone
• Ingest and de-identify clinical documents without losing meaning
• Design terminology-aware embeddings and indexes
• Build retrieval that returns grounded, cited clinical answers
• and 4 more

Data Scientist to GenAI

841 interview questions for data scientists moving into GenAI, answered

• Bridge classical data science and GenAI in interview answers
• Use LLMs and embeddings as data science tools
• Build and evaluate RAG systems and analytics copilots
• Fine-tune models with a data-centric approach
• and 4 more

Finance RAG and Agents

250 interview questions on building RAG and agents for financial services, answered

• Explain where RAG and agents add value in finance, and which use cases to avoid or delay
• Ingest and chunk filings, statements and contracts without losing numbers, periods or context
• Design entity-aware embeddings and indexes for financial language and identifiers
• Build retrieval that returns grounded, cited and numerically correct answers
• and 4 more

Forward Deployed Engineering

604 interview questions with the answers an interviewer is listening for

• Explain what an FDE owns, and how the role differs from software, solutions and consulting
• Run a discovery conversation that finds the problem behind the request
• Talk through integration, data and migration work in an estate you do not control
• Design and defend a RAG or agent solution, including how you would evaluate it
• and 3 more