Artificial Intelligence
Generative AI & LLM Engineering
Build real products on top of large language models.
Generative AI — Professional
Production LLM systems: fine-tuning, self-hosting, evaluation harnesses, guardrails and unit economics.
125 study hours
780 pages
12 modules
PDF ebook
What is inside
01
Fine-tuning and LoRA — when it is worth it
02
Dataset construction for fine-tuning
03
Self-hosting open models with vLLM and Ollama
04
Inference optimisation and GPU sizing
05
Prompt caching and cost reduction at scale
06
Building an evaluation harness and regression suite
07
Guardrails, moderation and prompt injection defence
08
Multi-agent orchestration and workflow design
09
Model routing and fallback strategies
10
Observability for LLM applications
11
Data privacy, retention and compliance
12
Unit economics: cost per user, per query, per outcome
By the end you can
- Run LLM applications reliably at production scale
- Defend an AI product against prompt injection and abuse
- Control and forecast AI infrastructure cost