AI Engineering Foundations

ai engineering course, rag pipeline tutorial, fine-tuning vs rag, prompt engineering for developers, structured outputs llm, context engineering, llm inference optimization, dpo grpo post-training, multimodal ai engineering, free ai engineering course

practitioner

en

• Write structured, testable prompts that behave like programs
• Build a RAG pipeline end to end: chunk, embed, store, retrieve, augment, generate
• Apply hybrid retrieval and chunking strategies and evaluate RAG quality
• Generate type-safe structured outputs with constrained decoding and schema engineering
• Decide between prompting, RAG, and fine-tuning, then run SFT or LoRA
• Process images, PDFs, documents, and video in multimodal pipelines
• Cut latency and cost with prompt caching, KV-cache, batching, and token budgeting
• Choose a post-training method (DPO, GRPO, KTO) for a given task

• Url: https://aiacademy.anthropos.work/chapters/ai-foundations-intro/ · AI Engineering Foundations: Intro · Position: 1 · The map of the AI Engineering Foundations skill path — what each chapter teaches, how they fit together, and where to start
• Url: https://aiacademy.anthropos.work/chapters/prompt-engineering-craft/ · Prompt Engineering Craft · Position: 2 · Write prompts that work like programs — structured, testable, and consistently effective
• Url: https://aiacademy.anthropos.work/chapters/context-engineering/ · Context Engineering · Position: 3 · Master the art and science of curating optimal context for AI agents
• Url: https://aiacademy.anthropos.work/chapters/structured-outputs/ · Structured Outputs · Position: 4 · Constrained decoding, schema engineering, and type-safe AI pipelines
• Url: https://aiacademy.anthropos.work/chapters/rag-foundations/ · RAG Foundations: From Chat to Retrieval · Position: 5 · Build the minimum viable RAG pipeline — chunk, embed, store, retrieve, augment, generate — in plain code
• Url: https://aiacademy.anthropos.work/chapters/rag-engineering/ · RAG Engineering · Position: 6 · Take the retrieval backbone to production — embeddings, chunking strategies, hybrid retrieval, advanced patterns, and evaluation. Assumes RAG Foundations.
• Url: https://aiacademy.anthropos.work/chapters/fine-tuning/ · Fine-Tuning for AI Engineers · Position: 7 · When to fine-tune vs RAG vs prompting — SFT, LoRA, dataset prep, and evaluation
• Url: https://aiacademy.anthropos.work/chapters/multimodal-ai/ · Multimodal AI Engineering · Position: 8 · Vision, document, PDF, and video processing — build with images and audio, not just text
• Url: https://aiacademy.anthropos.work/chapters/dataset-engineering/ · Dataset Engineering · Position: 9 · Build high-quality training and eval datasets — synthetic data, labeling, and curation pipelines
• Url: https://aiacademy.anthropos.work/chapters/inference-optimization/ · Prompt Caching & Inference Optimization · Position: 10 · Prompt caching, KV-cache, batching, speculative decoding, and token budgeting
• Url: https://aiacademy.anthropos.work/chapters/context-engineering-knowledge-systems/ · Context Engineering for Knowledge Systems · Position: 11 · Architect knowledge bases that AI agents can navigate, retrieve from, and act upon
• Url: https://aiacademy.anthropos.work/chapters/post-training-rl/ · Post-Training: DPO, GRPO & RL · Position: 12 · Pick the right post-training algorithm — DPO, GRPO, Dr-GRPO, DAPO, KTO, GiGPO — without drowning in research papers

• Write structured, testable prompts that behave like programs
• Build a RAG pipeline end to end: chunk, embed, store, retrieve, augment, generate
• Apply hybrid retrieval and chunking strategies and evaluate RAG quality
• Generate type-safe structured outputs with constrained decoding and schema engineering
• Decide between prompting, RAG, and fine-tuning, then run SFT or LoRA
• Process images, PDFs, documents, and video in multimodal pipelines
• Cut latency and cost with prompt caching, KV-cache, batching, and token budgeting
• Choose a post-training method (DPO, GRPO, KTO) for a given task

It is built for software engineers and developers who want to ship real AI features, not just experiment with chatbots. It assumes you can read and write code and want to understand the techniques behind RAG, fine-tuning, and structured generation.

Course Mode: online · Course Workload: PT257M · Mode: online