agent-interview-hub

<div align="center"> # Tool List **The most comprehensive AI Agent engineer interview knowledge base** [](https://github.com/Zchary1106/agent-interview-hub/stargazers) [](https://github.com/Zchary1106/agent-interview-hub/network/members) [](LICENSE) [](https://github.com/Zchary1106/agent-interview-hub/commits/main) **300+ interview questions (all with answers) · 14 company job requirements and interview experiences (including top overseas AI companies like Anthropic) · 6 practical exam questions · 16-week complete learning roadmap** [📖 Read online](https://zchary1106.github.io/agent-interview-hub/) · [⭐ Star support](https://github.com/Zchary1106/agent-interview-hub) · [🐛 Submit interview experience](https://github.com/Zchary1106/agent-interview-hub/issues) </div> --- ## 📌 What is this? A one-stop interview knowledge base for **AI Agent engineers** in top domestic companies looking to switch jobs or seek employment. - 🎯 **Who is it for?** — Engineers preparing to switch to Agent positions in top companies like Alibaba, ByteDance, Tencent, and Baidu. - 📚 **What does it include?** — 300+ high-frequency interview questions (all with answers), 9 company job requirements and real interview experiences, 6 timed practical exam questions, and 20 in-depth technical documents. - 🗺️ **Learning roadmap** — A 16-week complete learning plan from scratch to getting an offer. - ✨ **Features** — All questions come with answers, interview experiences are shared from real users on Niuke, and support GitHub Pages for online browsing. --- ## 🧭 Knowledge system ``` AI Agent Engineer Knowledge System │ ├── 🧱 Foundation │ ├── Transformer architecture and attention mechanism │ ├── LLM principles / Tokenization / Embedding │ └── Prompt Engineering basics │ ├── 🔧 Core │ ├── Agent design patterns (ReAct / Plan-and-Execute / Multi-Agent) │ ├── RAG full chain (retrieval / segmentation / reordering / generation) │ ├── Function Calling / Tool Use 🆕 │ ├── MCP (Model Context Protocol) 🆕 │ ├── Mainstream frameworks (LangChain / LangGraph / AutoGen) │ └── Context Engineering │ ├── 🚀 Advanced │ ├── Agentic RAG / GraphRAG │ ├── Agentic Coding and AI programming tools 🆕 │ ├── Model fine-tuning / inference optimization / quantization deployment │ └── Agent security, evaluation, and alignment │ └── 💼 Practical ├── System design and project experience ├── Job requirements interpretation of top companies └── Interview skills and real interview experiences ``` --- ## 🗺️ Learning Roadmap > 16 weeks from basics to offer, with clear goals and recommended resources each week ➡️ [**Agent Engineer Learning Roadmap.md**](Agent%E5%B7%A5%E7%A8%8B%E5%AD%B6%E4%B9%85%E8%B7%AD%E8%B5%B7%E5%9B%BE.md) --- ## 📚 General Knowledge ### 🔧 Core Technology | # | Document | Introduction | |---|------|------| | 1 | [Agent Core Concepts and Design Patterns](通用知识/Agent核心概念与设计模式.md) | Core paradigms like ReAct, Plan-and-Execute, and Multi-Agent | | 2 | [Agent Framework Overview](通用知识/Agent框架全景.md) | Overview of mainstream frameworks like LangChain, AutoGen, and CrewAI | | 3 | [LangChain and LangGraph In-Depth Analysis](通用知识/LangChain与LangGraph深度解析.md) | Evolution and practice of chain calls to graph orchestration | | 4 | [RAG Core Knowledge and Interview Questions](通用知识/RAG核心知识与面试题.md) | Retrieval-enhanced generation full chain: segmentation, retrieval, reordering, and generation | | 5 | [Agentic RAG and GraphRAG In-Depth Analysis](通用知识/Agentic%20RAG与GraphRAG深度解析.md) | From naive RAG to agent-driven intelligent retrieval | | 6 | [Context Engineering](通用知识/Context%20Engineering上下文工程.md) | Context window management, compression, and optimization strategies (including Anthropic's latest practices) 🔄 | | 7 | [Agent Security and Evaluation System](通用知识/Agent安全与评估体系.md) | Prompt injection defense, hallucination detection, and evaluation frameworks | | 8 | [Large Model Inference Optimization and Deployment](通用知识/大模型推理优化与部署.md) | Quantization, distillation, KV Cache, vLLM, and other inference acceleration | | 9 | [Function Calling and Tool Use](通用知识/Function%20Calling与Tool%20Use专题.md) | Comparison of implementations by three major manufacturers, calling patterns, and security defense 🆕 | | 10 | [MCP and Tool Ecosystem](通用知识/MCP与工具生态.md) | Model Context Protocol architecture, development practice, and enterprise applications 🆕 | | 11 | [Agentic Coding and AI Programming Tools](通用知识/Agentic%20Coding与AI编程工具.md) | Comparison of Claude Code, Cursor, and Copilot, hooks, and human-computer collaboration 🆕 | ### 📝 Interview Question Bank | # | Document | Introduction | |---|------|------| | 12 | [Latest AI Agent Interview Experience Index (2026)](通用知识/最新AI-Agent面经索引.md) | Latest interview experience entries from public sources like Niuke, Xiaohongshu, Zhihu, CSDN, and GitHub | | 13 | [Core Concept Explanation and Reference Answers](通用知识/核心概念详解与参考答案.md) | High-frequency concept questions and standard answers | | 14 | [Complete Answers to Eight Stock Questions](通用知识/八股文完整答案集.md) | 69 stock questions with detailed answers | | 15 | [Eight Stock Question Bank - DataWhale Open Source](通用知识/八股文题库-DataWhale开源.md) | DataWhale community-selected question bank | | 16 | [High-Frequency Questioning - Niuke Hot Post](通用知识/高频拷打题-牛客热帖.md) | Collection of high-praise interview questions from Niuke forum | | 17 | [Technical Knowledge Summary](通用知识/技术知识点汇总.md) | Quick reference manual: key knowledge points | | 18 | [Other Company Interview Experiences - Kuaishou, Ctrip, etc.](通用知识/其他公司面经-快手携程等.md) | Supplementary interview experiences from companies like Kuaishou and Ctrip | ### 🌐 Advanced Interview Questions | # | Document | Introduction | |---|------|------| | 19 | [Agent Core Concept Interview Questions - Advanced](通用知识/Agent核心概念面试题-进阶篇.md) | Advanced high-frequency questions and answers on core concepts | | 20 | [System Design Interview Questions - Advanced](通用知识/系统设计面试题-进阶篇.md) | Advanced system design questions and reference answers | | 21 | [AI Collaboration and Engineering Interview Questions - Advanced](通用知识/AI协作与工程化面试题-进阶篇.md) | Advanced AI collaboration and engineering questions and answers | --- ## 🎯 Practical Exam Questions (Timed Challenge) > From the [agent-interview-prep](https://github.com/Zchary1106/agent-interview-prep) project, simulating real interview scenarios with timed programming questions | # | Question | Difficulty | Time Limit | |---|------|:----:|:----:| | 1 | [Intelligent Document Q&A Agent](项目实战/实操考题/01-智能文档问答Agent.md) | ⭐⭐ | 4-6h | | 2 | [Multi-Agent Team Collaboration](项目实战/实操考题/02-多Agent团队协作.md) | ⭐⭐ | 4-6h | | 3 | [ReAct Mode Agent](项目实战/实操考题/03-ReAct模式Agent.md) | ⭐⭐ | 3-5h | | 4 | [AI Timed Full-Stack Development](项目实战/实操考题/04-AI限时全栈开发.md) | ⭐⭐ | 2-3h | | 5 | [AI Debugging Challenge](项目实战/实操考题/05-AI调试挑战.md) | ⭐⭐⭐ | 1-2h | | 6 | [AI Code Review Agent](项目实战/实操考题/06-AI-CodeReview-Agent.md) | ⭐⭐⭐ | 4-6h | --- ## 🏢 Domestic Top Company Interview Experiences | Company | Job Requirements | Interview Questions | Real Interview Experience | |------|:--------:|:------:|:--------:| | [Alibaba](阿里巴巴/) | ✅ | ✅ | ✅ | | [ByteDance](字节跳动/) | ✅ | ✅ | ✅ | | [Xiaohongshu](小红书/) | ✅ | ✅ | ✅ | | [Baidu](百度/) | ✅ | ✅ | — | | [Tencent](腾讯/) | ✅ | ✅ | — | | [Meituan](美团/) | ✅ | ✅ | ✅ | | [Ant Group](蚂蚁集团/) | ✅ | ✅ | ✅ | | [Huawei](华为/) | ✅ | ✅ | ✅ | | [Kuaishou](快手/) | ✅ | ✅ | ✅ | ## 🌍 Overseas Top AI Company Interview Experiences | Company | Job Requirements | Interview Questions | Real Interview Experience | |------|:--------:|:------:|:--------:| | [OpenAI](OpenAI/) | ✅ | ✅ | ✅ | | [Anthropic](Anthropic/) 🆕 | ✅ | ✅ | ✅ | | [Google (Google DeepMind)](谷歌/) | ✅ | ✅ | — | | [Microsoft](微软/) | ✅ | ✅ | — | | [Startups](初创公司/) | ✅ | ✅ | — | > 📖 Overseas Company Comprehensive Strategy: [Overseas Top AI Company Interview Strategy-2026](通用知识/海外顶级AI公司面试攻略-2026.md) 🆕 --- ## 🚀 Usage Guide ### Online Reading (Recommended) Access the GitHub Pages site, mobile-friendly: 👉 **https://zchary1106.github.io/agent-interview-hub/** ### Local Reading ```bash git clone https://github.com/Zchary1106/agent-interview-hub.git cd agent-interview-hub # Open with any Markdown editor ``` ### Local Static Site Building ```bash python3 -m pip install -r requirements.txt python3 scripts/build_site.py python3 -m http.server 8000 -d dist ``` The generated result will be output to `dist/`. GitHub Pages automatically builds and deploys after pushing to the `main` branch via `.github/workflows/pages.yml`. ### Installing Interview Experience Collector Agent This repository includes an Interview Collector Agent for searching interview experiences from public sources like Niuke, Xiaohongshu, Zhihu, CSDN, and GitHub. ```bash bash agents/interview-collector/install.sh --targets copilot,claude,cursor,generic ``` Supports installation on: | Platform | Write Location | |---|---| | GitHub Copilot CLI | `~/.copilot/instructions/interview-collector.instructions.md` | | Claude Code | `~/.claude/skills/interview-collector/SKILL.md` | | Cursor | `.cursor/rules/interview-collector.mdc` | | Generic/Domestic Agent | `~/.agent-interview-hub/interview-collector/AGENT.md` | See [Interview Collector Agent Instructions](agents/interview-collector/README.md) for details. Complete collection process can also be run with scripts: ```bash # 1. Check local search/reading tools python3 scripts/collect_interviews.py doctor # 2. Search public sources, generate candidate JSON and Markdown report python3 scripts/collect_interviews.py search \ --platform nowcoder \ --platform zhihu \ --platform blogs \ --platform github \ --query "AI Agent large model interview experience 2026" \ --output data/interview_candidates.json \ --report data/interview_candidates.md # 3. After manual or agent review of candidates, organize into data/interviews.json python3 -m json.tool data/interviews.json python3 scripts/build_site.py ``` If OpenCLI is configured locally, Xiaohongshu search can also be added: ```bash python3 scripts/collect_interviews.py search \ --platform xiaohongshu \ --query "AI Agent interview experience" \ --append ``` ### Recommended Reading Order 1. 📖 Read the [Learning Roadmap](Agent%E5%B7%A5%E7%A8%8B%E5%AD%B6%E4%B9%85%E8%B7%AD%E8%B5%B7%E5%9B%BE.md) to understand the overall process 2. 🧱 Read through [Agent Core Concepts and Design Patterns](通用知识/Agent核心概念与设计模式.md) 3. 🔧 Dive into [RAG](通用知识/RAG核心知识与面试题.md) and [LangChain/LangGraph](通用知识/LangChain与LangGraph深度解析.md) 4. 🆕 Master [Function Calling](通用知识/Function%20Calling与Tool%20Use专题.md) and [MCP](通用知识/MCP与工具生态.md) (2025 high-frequency new topics) 5. 📝 Brush through [Complete Answers to Eight Stock Questions](通用知识/八股文完整答案集.md) (69 questions) 6. 🏢 Look at corresponding interview experiences for target companies 7. 🔥 Finally, use [High-Frequency Questioning](通用知识/高频拷打题-牛客热帖.md) to fill gaps --- ## 🤝 Contribution Guide Welcome all forms of contributions! - **📝 Submit interview experiences** — Share your interview experiences through [Issues](https://github.com/Zchary1106/agent-interview-hub/issues) - **🔧 Submit PR** — Supplement questions, correct answers, and add company interview experiences - **⭐ Star** — The simplest way to support, let more people see ### Contribution Steps ```bash # 1. Fork this repository # 2. Create a branch git checkout -b feat/add-xxx-interview # 3. Commit changes git commit -m "feat: Add xxx interview experience" # 4. Push and create PR git push origin feat/add-xxx-interview ``` --- ## 📈 Star History <a href="https://star-history.com/#Zchary1106/agent-interview-hub&Date"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=Zchary1106/agent-interview-hub&type=Date&theme=dark" /> <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=Zchary1106/agent-interview-hub&type=Date" /> <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=Zchary1106/agent-interview-hub&type=Date" /> </picture> </a> --- ## 📄 License This project is open-sourced under the [MIT License](LICENSE). --- <div align="center"> **If this project helps you, give it a ⭐ Star support!** Made with ❤️ for AI Agent Engineers </div>