This course develops the technical foundations and applied engineering skills required to build, evaluate, and deploy generative AI solutions in organizational settings. Students begin with the conceptual architecture of modern generative models – transformers, pretraining and alignment, context windows, and multimodal and diffusion models – and progress to hands-on work with production LLM systems: prompt engineering and structured outputs, retrieval-augmented generation over enterprise data, function calling, fine-tuning and adaptation strategies, and systematic evaluation of stochastic model behavior including hallucination, bias, and regression testing. Throughout, technical choices are framed as business decisions: build-versus-buy and model selection, cost-latency-quality trade-offs, data governance and privacy in retrieval pipelines, and responsible-deployment guardrails.