练完一遍了? 用英文写下回答,粘贴到免费自查工具打分(工具按英文要点评分)
- 01初级什么是 RAG(检索增强生成)?What is RAG (retrieval-augmented generation)?
- 02初级讲一讲 Transformer 架构Explain the transformer architecture
- 03中级什么是 KV cache,它为什么对推理很重要?What is the KV cache and why does it matter for inference?
中文手册 · 2026 版如何从0到1准备AI Engineer面试
20 章、5 套答题框架(FLAME、SPARK、FORGE、RISE、EMBER)、100 道题库和 8 周备考计划。
- 出版Valenx Press
- 格式Gumroad 电子版下载
- 价格$9.99
获取中文手册 优惠码 EARLYBF 立减 40%,截至太平洋时间 11 月 3 日 23:59更想读英文版?The 0→1 AI Engineer Interview Playbook,$19.99,Gumroad 英文版。也可以先免费领取 Top 30 题 PDF(英文)。
- 04中级LLM 为什么会产生幻觉,怎样减少?Why do LLMs hallucinate, and how do you reduce it?
- 05高级什么是 prompt injection(提示词注入),怎么防御?What is prompt injection and how do you defend against it?
- 06中级讲一讲 LoRA 和 QLoRAExplain LoRA and QLoRA
- 07中级RAG 和 fine-tuning(微调)分别在什么时候用?RAG vs fine-tuning: when should you use each?
- 08中级你怎样评估一个 LLM?How do you evaluate an LLM?
- 09高级你怎样评估一个 RAG 系统?How do you evaluate a RAG system?
- 10初级什么是 AI agent(智能体),它和 chain 有什么区别?What is an AI agent, and how is it different from a chain?
- 11中级预训练、指令微调和 RLHF 有什么区别?What is the difference between pre-training, instruction tuning and RLHF?
- 12高级什么是 LLM scaling laws(缩放定律),它如何影响决策?What are LLM scaling laws and how do they change decisions?
- 13初级LLM 中的 tokenization(分词)是什么,为什么重要?What is tokenization in LLMs and why does it matter?
- 14初级什么是 context window(上下文窗口),它如何影响系统设计?What is a context window and how does it affect system design?
- 15初级LLM 中的 temperature 和 top-p 分别起什么作用?What do temperature and top-p do in an LLM?
- 16中级什么是 LLM 量化(quantization),它为什么对部署很重要?What is LLM quantization and why does it matter for deployment?
- 17高级什么是 Mixture of Experts(MoE,混合专家模型),有哪些取舍?What is Mixture of Experts (MoE) and what are its trade-offs?
- 18中级推理模型(reasoning model)和普通对话模型有什么不同?How do reasoning models differ from standard chat models?
- 19初级embedding 模型和生成式模型有什么区别?What is the difference between an embedding model and a generative model?
- 20中级什么是 chain-of-thought prompting(思维链提示),什么时候有用?What is chain-of-thought prompting and when does it help?
免费工具
English version: AI engineer interview question deep dives
中文手册想要完整的中文备考方法?
《如何从0到1准备AI Engineer面试》:20 章、5 套答题框架(FLAME、SPARK、FORGE、RISE、EMBER)、100 道题库和 8 周备考计划。
获取中文手册 优惠码 EARLYBF 立减 40%,截至太平洋时间 11 月 3 日 23:59更想读英文版?The 0→1 AI Engineer Interview Playbook,$19.99,Gumroad 英文版。也可以先免费领取 Top 30 题 PDF(英文)。