AI Application Engineering

AIV 401 — Python for AI I

Learn the Python you actually need for AI work: how to read and write real code, debug when things break, and use AI coding tools without letting them do your thinking for you.

AIV 402 — Python for AI II

A practical Python course covering the tools and patterns that show up in real AI and data projects: packages, NumPy, pandas, HTTP APIs, testing, and code quality, ending with a pipeline you can put in a portfolio.

AIV 403 — Git, GitHub & Developer Workflows

Build practical competency in git, GitHub, and AI-assisted developer workflows through executable work, debugging, evaluation, and a portfolio-grade final project. Aiversity 400-track master specification, delivered on Honen.

AIV 404 — SQL & Databases

Learn to design databases, write SQL queries, and keep data consistent and fast, the skills behind every product that stores and retrieves information.

AIV 405 — Data Engineering for AI

Most AI projects don't fail on the model. They fail on the data feeding it. This course teaches you to build reliable data pipelines that take raw, messy inputs and produce clean, validated, model-ready outputs.

AIV 406 — Embeddings

Learn how text becomes searchable vectors, which models and chunking strategies actually work in production, and how to measure whether your retrieval system is doing its job.

AIV 407 — Vector Databases

Learn how vector databases actually work, from storage and indexing to hybrid retrieval and production ops, by building and running real systems in code.

AIV 408 — RAG Fundamentals

RAG is how you give an LLM access to your documents without retraining it. This course walks you through building a complete retrieval-augmented generation pipeline from scratch, covering ingestion, chunking, embeddings, retrieval, and evaluation.

AIV 409 — Advanced RAG

Most RAG systems underperform not because the model is bad, but because the retrieval is. This course covers the techniques that actually move the needle: query transformation, hybrid search, reranking, contextual retrieval, chunking strategy, and evaluation.

AIV 410 — Graph RAG & Knowledge Graphs

Build a Graph RAG system from scratch: model knowledge as a graph, extract entities from text with an LLM, query the graph, and wire it into a retrieval pipeline that gives an LLM the right context to actually answer questions.

AIV 411 — AI Evaluation

Most teams know when their AI feature feels wrong. This course teaches you how to prove it, measure it, and fix it — with evals that hold up under pressure.

AIV 412 — Production AI Systems

Most AI projects work on a laptop and break in production. This course covers the engineering layer between a working model and a system that actually holds up: deployment, security, observability, reliability, and cost.