AI engineering
AI engineering is the work of building software around machine learning models: retrieving the right information, understanding how the models work, and running them inside real products.
A topic guide by Parsa Alizadeh: one article to start with, deeper articles, and the projects where it comes up in real work.
Start here
Go deeper
The Transformer, from the original paper: attention explained for developers
How scaled dot-product attention, multi-head attention and positional encoding work, with the formulas and settings taken directly from "Attention Is All You Need".
AI3 min read
How language models read text: tokens, byte pair encoding, and why Persian costs more
What a token is, how byte pair encoding builds a vocabulary, why Persian and Turkish take more tokens than English, and how to count tokens instead of guessing.
AI4 min read
How vector search finds neighbours fast: embeddings, similarity and HNSW
Why exact nearest-neighbour search does not scale, what approximate search trades away, and how the HNSW graph from Malkov and Yashunin's paper finds close vectors quickly.
AI3 min read
How to evaluate a RAG system: retrieval metrics, faithfulness and LLM judges
Measure retrieval and generation separately, with recall@k, MRR and nDCG for the retriever and faithfulness for the answer, and what research says about using language models as judges.
AI5 min read
Quantizing large language models: how 8-bit and 4-bit weights work
Why a 7-billion-parameter model needs 14 GB in 16-bit, how quantization shrinks it, why outliers make it hard, and what LLM.int8(), GPTQ, AWQ and QLoRA each changed.
AI5 min read