0/10in AI/ML Engineering
Module

AI/ML Engineering

The AI Software Engineer role is applied, not academic. This module is about wiring models into products: tokens, embeddings, retrieval, agents, serving trade-offs, and the evaluation loops that keep quality from silently regressing.

10 lessons · ~154 min total
Start the first lesson →
1

The AI Engineer's Mental Model

Where the AI SWE sits between research and product, the shape of an LLM call, and the vocabulary the rest of the module builds on.

Not started
2

Tokens, Sampling & Prompting

How text becomes tokens, what temperature and top-p actually do, and prompt structures that make outputs reliable.

Not started
3

Embeddings & Vector Search

How meaning becomes geometry. Drag a query around a 2D vector space and watch cosine similarity rank the neighbors.

Not started
4

Vector Databases & ANN Indexes

Exact search does not scale. HNSW, IVF, and the recall-vs-latency knobs behind every production vector store.

Not started
5

Retrieval-Augmented Generation

Ground a model in your own data. Trace a question through chunking, retrieval, and generation stage by stage.

Not started
6

Prompting vs. RAG vs. Fine-tuning

The three levers for changing model behavior, what each is good and bad at, and how to choose without guessing.

Not started
7

Agents, Tools & Function Calling

Let a model take actions. The reason–act loop, tool schemas, and the failure modes that make agents hard in production.

Not started
8

Evaluation & Guardrails

You cannot improve what you cannot measure. Offline evals, LLM-as-judge, online signals, and safety guardrails.

Not started
9

Serving, Latency & Cost

Batching, KV-caches, streaming, and quantization. The engineering that decides whether your feature is affordable.

Not started
10

MLOps & the Model Lifecycle

Versioning data, models, and prompts; safe rollouts; and catching drift before users do. Keeping a live system healthy.

Not started