Plus
AI engineering·Retrieval
Design a retrieval-augmented generation system
Answer questions from a changing document collection with traceable sources.
Advanced 60 min
AI engineer system design interview questions
AI engineering interviews ask you to design products on large language models. These rounds cover ChatGPT, retrieval-augmented generation (RAG) over company documents, a customer support AI agent, an AI code assistant, a real-time voice agent, text-to-image generation, document ingestion for RAG, an AI answer engine, an LLM gateway, an LLM inference platform and an LLM evaluation platform.
Practice what interviewers probe: estimating in tokens, context and retrieval design, tool contracts and approvals for agents, evaluation with golden datasets and calibrated judges, guardrails and prompt injection, streaming and GPU capacity, and cost per task.
Free
AI engineering·Assistants
Design ChatGPT
Serve a chat assistant to millions of people with streamed answers, saved history and fair usage limits.
Advanced 60 min
Free
AI engineering·AI agents
Design a customer support AI agent
Resolve support chats with tools and refunds within policy, and hand off to a human when needed.
Advanced 60 min
Plus
AI engineering·Assistants
Design an AI code assistant
Suggest code as developers type, using context from their repository, in a few hundred milliseconds.
Advanced 60 min
Plus
AI engineering·AI agents
Design a real-time voice AI agent
Answer phone calls with an AI that listens, books appointments and replies without awkward pauses.
Advanced 60 min
Plus
AI engineering·Generative AI
Design a text-to-image generation service
Turn prompts into images in seconds for millions of users while keeping GPUs busy and output safe.
Advanced 60 min
Plus
AI engineering·Retrieval
Design a document ingestion pipeline for RAG
Parse, chunk and index millions of PDFs, scans and office files so LLM apps can search them.
Advanced 60 min
Plus
AI engineering·Retrieval
Design an AI answer engine
Answer questions from the live web with cited sources in a few seconds, like Perplexity.
Advanced 60 min
Plus
AI engineering·LLM infrastructure
Design an LLM gateway
Give every team one safe way to call many model providers, with routing, fallbacks and budgets.
Intermediate 45 min
Plus
AI engineering·LLM infrastructure
Design an LLM inference platform
Serve open-weight LLMs on a GPU fleet with high throughput and predictable latency.
Advanced 60 min
Plus
AI engineering·Model quality
Design an LLM evaluation platform
Let teams test prompt, model and agent changes against golden datasets before they ship.
Intermediate 45 min