A comprehensive guide to AI engineering for experienced software developers, covering the full stack from foundation model basics to production agent deployment. Topics include choosing and adapting LLMs (prompt engineering, RAG, finetuning), evaluation pipelines (LLM-as-judge, red teaming, domain-specific metrics), advanced RAG techniques (hybrid search, reranking, chunking strategies, embedding strategies), summarization patterns (MapReduce), chatbot memory management, prompt security (injection, jailbreaking), structured outputs, sampling parameters, test-time compute, and observability. Practical Python code examples use the OpenAI API and LangChain throughout, with a GCP/Vertex AI bias for infrastructure.
Table of contents
Introduction to AI EngineeringUnderstanding Foundation ModelsPrompting and Prompt EngineeringEvaluationSummarization ApplicationsRetrieval-Augmented Generation (RAG)Advanced RAGFinetuningDataset EngineeringInference OptimizationAI AgentsMulti-Agent Systems and Agent ProtocolsProduction AI ArchitectureBuilding on Google CloudClosing1.1K Impressions