Learn GenAI
The Course Atlas
Every track and module, from first tokens to production agents. Follow the dotted route in order, or select a landmark to see its pages.
- Module landmark
- Learning route
- Capstone projects
- You are hereYour last page
Map index - every page
Foundations
01. LLM Foundations
02. Prog Langs
- Overview
- Appendix - Summary & Key Terms
- Python for AI Engineering
- API Design for LLM Services
- Git Workflows for ML
- Linux & the GPU Box
- Q&A Review Bank
- Overview
- Appendix - Summary & Key Terms
- Tensors & Autograd
- Dataset & DataLoader
- Training Loop From Scratch
- Checkpointing & Mixed Precision
- Debugging & GPU Memory
- PyTorch for LLMs
- Q&A Review Bank
- Raw PyTorch Classifier
- GPT From Scratch
Building Models
04. Pretraining at Scale
05. Post-Training & Reasoning
06. Fine-Tuning Lab
Serving & Production
08. Inference & Serving
09. Production Engineering
- Overview
- Appendix - Summary & Key Terms
- Docker for GPU Inference
- Kubernetes & Helm
- Model Lifecycle & Rollout
- Security & Compliance
- LLM Serving on Kubernetes
- Observability, SLOs & Incidents
- Cloud Networking & IAM for AI
- Infrastructure as Code
- Q&A Review Bank
- Helm Chart & Release Checklist
- Terraform Private Endpoint & SLO Alerts
Building Apps
11. Prompt & Context Engineering
12. RAG
- Overview
- Appendix - Summary & Key Terms
- RAG Fundamentals
- Embeddings & Vector Search
- Document Processing & Chunking
- Retrieval & Reranking
- Grounded Generation & Citations
- RAG Evaluation
- Advanced RAG Patterns
- Agentic & Deep-Research RAG
- Long Context vs RAG vs CAG
- Enterprise Data Integration
- RAG System Design
- RAG in Production
- Managed RAG on Cloud Platforms
- Q&A Review Bank
- Retrieval Evaluation
- Simple RAG Pipeline
- Agentic RAG - Hybrid Vector + Graph