references

References — Interview Prep

Practice & Learning

• https://docs.anthropic.com/en/docs/build-with-claude — Anthropic build guides: read every section, the content matches what interviewers test
• https://github.com/anthropics/anthropic-cookbook — Working code examples for every Anthropic feature
• https://www.deeplearning.ai/courses — Short courses on RAG, agents, LangChain, prompt engineering (free audit)
• https://lmarena.ai — LLM Arena: understand how models benchmark against each other

Must-Read Papers (for depth questions)

• https://arxiv.org/abs/1706.03762 — Attention Is All You Need (2017) — transformer architecture
• https://arxiv.org/abs/2005.11401 — RAG paper (Lewis et al., 2020)
• https://arxiv.org/abs/2210.03629 — ReAct (Yao et al., 2022)
• https://arxiv.org/abs/2201.11903 — Chain-of-Thought Prompting (Wei et al., 2022)
• https://arxiv.org/abs/2307.03172 — Lost in the Middle (Liu et al., 2023)
• https://arxiv.org/abs/2212.10496 — HyDE (Gao et al., 2022)
• https://arxiv.org/abs/2306.05685 — Judging LLM-as-a-Judge (Zheng et al., 2023)

System Design Practice

• https://docs.anthropic.com/en/docs/build-with-claude/agents — Multi-agent patterns
• https://langchain-ai.github.io/langgraph/concepts — LangGraph architecture concepts
• https://docs.ragas.io — RAGAS: evaluation framework you’ll be asked about

Recommended Study Order

1. Re-read 00-foundations/README.md — be able to explain attention in 2 minutes
2. Work through question-bank.md — answer each question out loud before reading the model answer
3. Do all 3 system design walkthroughs in system-design/ as timed exercises (30 min each)
4. Skim the 3 must-read papers above — you don’t need every detail, just the key contributions
5. Run the examples in modules 02, 03, and 09 — hands-on beats reading for retention