University-style syllabus · 32 modules

GenAI Syllabus

A structured curriculum for Production LLM Engineering — Transformer foundations, fine-tuning and alignment, multimodal and speech AI, RAG and retrieval engineering, agentic systems, and prompt/context engineering. Each module lists topics, learning objectives, and the tools and frameworks referenced — concept-first, not a coding tutorial.

Sub-category·3 modules

Transformers and Architecture

Attention, tokenization, encoder/decoder families, fast inference, and scaling laws.

Sub-category·7 modules

LLM Fine-Tuning and Alignment

Pretraining lifecycle, SFT, PEFT, preference alignment, quantization, MoE, reasoning models, and SLMs.

M04Pre-TrainingPost-Training

Module 04: LLM Lifecycle and Pre-Training

The two-phase LLM lifecycle — pre-training vs post-training, why base models need adaptation, continued pre-training, and multi-token prediction.

May 28, 2026Open module
M05Data PreparationSynthetic Data

Module 05: Datasets and Synthetic Data

Preparing fine-tuning data — dataset formats, chat templates, loss masking, deduplication, and synthetic data with self-instruct and LLM-as-judge.

May 28, 2026Open module
M06SFTLoRA

Module 06: SFT, PEFT and Preference Alignment

Adapting and aligning LLMs — PEFT (LoRA, QLoRA, DoRA, AdaLoRA), supervised fine-tuning, and preference alignment with RLHF and DPO.

May 28, 2026Open module
M07EvaluationQuantization

Module 07: Evaluation, Quantization and Deployment

Post-fine-tuning workflows — benchmark and LLM-as-judge evaluation, quantization (GPTQ, AWQ, NF4, FP8, GGUF), and serving with vLLM and llama.cpp.

May 28, 2026Open module
M08Mixture of ExpertsMoE

Module 08: Mixture of Experts

Mixture of Experts — why dense models hit scaling limits, MoE routing, load balancing against expert collapse, and when MoE beats dense.

May 28, 2026Open module
M09Reasoning ModelsChain-of-Thought

Module 09: Reasoning Models and Chain-of-Thought

Reasoning models — what sets them apart from standard LLMs, chain-of-thought training, RL-only reasoning (GRPO, DeepSeek-R1-Zero), and distillation.

May 28, 2026Open module
M10Small Language ModelsKnowledge Distillation

Module 10: Small Language Models and Distillation

Small Language Models and distillation — why SLMs win on cost, latency, and privacy; student-teacher training, soft labels, and KL divergence.

May 28, 2026Open module
Sub-category·3 modules

Vision and Speech

CNNs to ViT, visual language models, and speech-to-text with Whisper.

Sub-category·6 modules

RAG and Retrieval

Embeddings, LangChain RAG, advanced RAG patterns, vector quantization, multimodal RAG, graph RAG and security.

Sub-category·4 modules

Agents and Multi-Agent Systems

Function calling, MCP, LangGraph, A2A protocol, observability, and Bedrock AgentCore deployment.

Sub-category·3 modules

Prompting, Context and Evaluation

Prompt engineering, context engineering, and evaluation harnesses with agent CI/CD.

Sub-category·6 modules

Capstone Projects

End-to-end projects integrating fine-tuning, distillation, RAG, multi-agent systems, speech, and LLMOps.

P01CapstoneFine-Tuning

Project 01: ClinicLLM — Medical LLM Fine-Tuning Pipeline

Build a domain-specific medical language model with QLoRA SFT and DPO preference alignment, then serve it with multiple hot-swappable LoRA adapters.

May 28, 2026Open module
P02CapstoneKnowledge Distillation

Project 02: TinyReason — Distilling Reasoning to a CPU Model

Compress a larger reasoning teacher into a small student using KL divergence and attention transfer, then quantize to GGUF for cost-efficient CPU inference.

May 28, 2026Open module
P03CapstoneRAG

Project 03: LegalRAG — Multi-Modal + Graph RAG

Build a legal-document intelligence system — ColPali multimodal indexing (no OCR), Neo4j knowledge graph, hybrid retrieval with RRF, RAGAS evals.

May 28, 2026Open module
P04CapstoneMulti-Agent

Project 04: DevOpsCrew — Multi-Agent DevOps with HITL and A2A

Build a production DevOps assistant with a LangGraph supervisor delegating to specialised sub-agents over MCP and A2A, with human-in-the-loop gating every write.

May 28, 2026Open module
P05CapstoneLLMOps

Project 05: EvalShip — Eval-Gated CI/CD with Auto-Rollback

Wrap all prior projects in a production LLMOps shell — every change passes eval-gated CI stages, with blue/green deploys and auto-rollback.

May 28, 2026Open module
P06CapstoneWhisper

Project 06: VoiceTrack — Whisper STT Pipeline

Fine-tune Whisper on domain-specific audio and ship a production STT service with streaming transcription, diarisation hooks, and an evaluation gate on WER.

May 28, 2026Open module