100+ tabs open.
Zero plan.
It’s time to SAADHO.

LLMs-from-scratch (GitHub) · 90 min

Chapter 4: Implementing a GPT model from Scratch To Generate Text

“Write a GPT block” and “walk me through the forward pass with shapes” are standard asks once attention is covered, and this notebook builds exactly that piece by piece.

Skip: gpt.py and previous_chapters.py are just packaged copies of the same code; the extra GPT-2 medium/large/XL configs in 4.6 unless you want the parameter-count practice.

Ragas docs · 25 min

List of available metrics

Ragas's metric names (faithfulness, context precision, context recall) are the shared vocabulary interviewers use when they ask how you'd evaluate a RAG system.

Skip: The “Nvidia Metrics”, “SQL”, “Agents or Tool use cases” sections, the Legacy Metrics API blocks, and the ID-based / non-LLM variants.

eugeneyan.com · 30 min

Product Evals in Three Simple Steps

The eval-design round asks you to build a working eval from nothing, out loud. This is a compact, practical recipe for exactly that: labels first, then a grader you’ve checked, then a harness that runs on every change.

Skip: Skim “Additional reading” and the course promotion; the three steps are the whole lesson.

Hugging Face blog · 30 min

How to generate text: using different decoding methods for language generation with Transformers

“What do temperature and top-p actually do?” is a standard warm-up question, and this post builds each method on the previous one with runnable examples.

Skip: The “Appendix” links. Don't try to match the printed GPT-2 outputs word for word, and expect a couple of typos in the code comments.

Dropbox Tech Blog · 35 min

Building Dash: How RAG and AI agents help us meet the needs of businesses

This is a real team explaining how they built a knowledge assistant over many business apps, with the trade-offs an interviewer will probe: retrieval choice, freshness, latency, and evaluation.

Skip: Skim “The role of AI agents” stages unless the interviewer asks about multi-step questions; the core case is retrieval.

GreatFrontEnd · 45 min

Answering “Tell Me About Yourself”

Almost every round opens with “tell me about yourself”, and the answer decides which parts of your background the interviewer digs into. A tight, role-specific pitch gives you that control from the first minute.

Skip: Skip “Portfolio showcase” unless you have a demo worth showing, and swap the front end pitch points for your own LLM work (evals, retrieval, latency or cost wins). The end-of-page exercises are optional.

Python documentation · 40 min

Coroutines and tasks

“Call the model for these 500 prompts concurrently with a timeout” is a standard LLM-engineer coding prompt, and it is solved with exactly the primitives on this page.

Skip: “Eager task factory”, “Shielding from cancellation”, “Scheduling from other threads”, “Introspection” and the “Task object” reference.

jalammar.github.io · 40 min

The Illustrated Word2vec

“How are embeddings trained?” is the standard warm-up before any RAG or retrieval question, and word2vec with negative sampling is the canonical answer interviewers expect you to sketch.

Skip: “Personality Embeddings: What are you like?” if you already have the vector intuition, and “References & Further Readings”.