Phase 11

LLM Engineering

Put LLMs to work in production applications.

01Prompt Engineering: Techniques & PatternsBuild~90 minutesQuiz 02Few-Shot, Chain-of-Thought, Tree-of-ThoughtBuild~45 minutesQuiz 03Structured Outputs: JSON, Schema Validation, Constrained DecodingBuild~90 minutesQuiz 04Embeddings & Vector RepresentationsBuild~75 minutesQuiz 05Context Engineering: Windows, Budgets, Memory, and RetrievalBuild~90 minutesQuiz 06RAG (Retrieval-Augmented Generation)Build~90 minutesQuiz 07Advanced RAG (Chunking, Reranking, Hybrid Search)Build~90 minutesQuiz 08Fine-Tuning with LoRA & QLoRABuild~75 minutesQuiz 09Function Calling & Tool UseBuild~75 minutesQuiz 10Evaluation & Testing LLM ApplicationsBuild~45 minutesQuiz 11Caching, Rate Limiting & Cost OptimizationBuild~45 minutesQuiz 12Guardrails, Safety & Content FilteringBuild~45 minutesQuiz 13Building a Production LLM ApplicationBuild (Capstone)~120 minutesQuiz 14Model Context Protocol (MCP)Build~75 minutesQuiz 15Prompt Caching and Context CachingBuild~60 minutesQuiz 16Agent State Machines — Graphs, Nodes, CheckpointsBuild~75 minutesQuiz 17Agent Framework Tradeoffs — Graph, Role, and Actor OrchestrationLearn~45 minutesQuiz

“Stay hungry, stay foolish.”

— Steve Jobs