AI

Trace the conceptual hierarchy from artificial intelligence and machine learning to deep learning, language models, and AI engineering.

Explore probabilistic language modeling, tokens and vocabularies, and the difference between masked and autoregressive models.

Follow how large language models are built, from data preparation and architecture to training, inference, scaling, and optimization.

Understand foundation models and survey representative models for text, images, speech, and other modalities.

Examine why AI engineering emerged, how it differs from conventional software development, and what its application stack involves.

Review the conventional software delivery lifecycle, from requirements and research to implementation, testing, performance, and operations.

A structured guide to retrieval-augmented generation: motivation, indexing, retrieval, context assembly, optimization, and evaluation.

Understand AI agents through tool use, planning, the ReAct pattern, and the challenges of reliable multi-step execution.

Examine when fine-tuning helps, how it compares with prompting and RAG, and how to train, optimize, and evaluate adapted models.

Explore prompt structure, context, examples, constraints, security risks, and practical ways to improve model instructions.

Distinguish model knowledge, short-term context, and long-term memory, with an emphasis on storage, retrieval, and lifecycle management.

Organize practical AI evaluation around criteria, measurement methods, model selection, and evidence-based decisions.

Survey the dataset engineering lifecycle: requirements, acquisition, synthesis, cleaning, validation, and quality control.

Connect gateways, context engineering, guardrails, caching, agents, and observability with a user-feedback loop.

Study inference optimization through latency, throughput, memory use, and cost across models, runtimes, and serving systems.

Map the AI technology stack into four layers: compute infrastructure, models, application platforms, and AI applications.