A Cram Sheet for the AI Engineering Hype Cycle

What it does

This repository is a sprawling study guide for AI engineering interviews. It collects a large set of questions across LLM fundamentals, RAG, agents, fine-tuning, quantization, and system design, pairing each with an answer or an external link to a blog post, video, or social thread. Think of it as a syllabus for the current AI job market, maintained by the founder of an AI education platform.

The interesting bit

The breadth is the product. It treats nearly every hot topic in AI engineering—from KV caches and Flash Attention to MCP and reward hacking—as an interview question, forcing the reader to confront gaps in their knowledge rather than just reading passively. Many answers route to the author’s own Outcome School content, so the repo doubles as a well-organized index to a private curriculum.

Key highlights

• Covers the full stack: LLM internals, prompt engineering, RAG, vector DBs, AI agents, fine-tuning, LLMOps, and multimodal AI.
• Includes scenario-based “your LLM is doing X, how do you fix it?” questions that mirror real debugging.
• Answers range from inline explanations to links to dedicated blog posts and video deep-dives.
• Explicitly targets roles like AI Engineer, LLM Engineer, Agentic AI Engineer, and MLOps.
• Actively updated; the author notes new questions will be added over time.

Caveats

• Not all questions have self-contained answers; many are just outbound links to external content (some behind social-media walls).
• The repo is pure documentation—there is no code, runnable examples, or interactive components.

Verdict

Worth bookmarking if you are interviewing for an AI engineering role and want a structured map of what you might be asked. Skip it if you are looking for hands-on projects or open-source tools; this is a reading list, not a codebase.