Learning path
Generative AI Professional
A comprehensive, industry-grade learning path covering core AI engineering, neural architectures, vector search, retrieval-augmented generation (RAG), autonomous agents, LangGraph, Model Context Protocol (MCP), fine-tuning (LoRA/QLoRA), quantization, LLM serving, evaluation, and end-to-end production AI system architecture.
From foundational neural networks and transformers to RAG, multi-agent systems, fine-tuning, and production system design.
What you will learn
- Design and architect production-ready Generative AI systems from scratch
- Build advanced RAG pipelines with hybrid retrieval, reranking, and chunking strategies
- Develop autonomous single- and multi-agent workflows using LangGraph and MCP
- Fine-tune and optimize models with LoRA, QLoRA, and modern quantization techniques
- Deploy, serve, monitor, and evaluate LLMs at enterprise scale with automated testing
Who this is for
- Software engineers transitioning into AI engineering
- ML engineers looking to master modern generative AI architectures
- Technical leads and architects designing enterprise LLM applications
Skills covered
- Python for AI
- PyTorch
- NumPy
- Transformers
- Hugging Face
- Vector Search
- Embeddings
- RAG
- LangChain
- LlamaIndex
- Function Calling
- AI Agents
- LangGraph
- Multi-Agent Systems
- Model Context Protocol (MCP)
- LoRA
- QLoRA
- PEFT
- Quantization
- vLLM
- Docker
- MLOps
- LLMOps
- AI System Design
- AI Evaluation
Your course sequence
Beginner Bridge: Programming, Data and Debugging for GenAI
Required course · Premium access
Start without programming experience: learn terminal navigation, Python data flow, JSON, debugging, SQL and the mathematics needed for the28-phase GenAI engineering curriculum.
AI Engineering Foundations
Required course · Premium access
Refresh only the engineering foundations required to build and ship AI systems; do not restart beginner material. Learn through explicit calculations, executable experiments, guided repairs and independently assessed changes.
Neural Network Foundations
Required course · Premium access
Understand and implement the core mechanics of a neural network before using deep learning frameworks. Learn through explicit calculations, executable experiments, guided repairs and independently assessed changes.
Activation Functions for Neural Networks
Required course · Premium access
Master the engineering purpose and behavior of common activation functions without research-level derivations. Learn through explicit calculations, executable experiments, guided repairs and independently assessed changes.
Multi-Layer Neural Networks From Scratch
Required course · Premium access
Build a complete feed-forward neural network from scratch and understand the full training pipeline. Detailed engineering lessons with worked calculations, complete CPU labs, failure diagnosis, independent challenges and instructor capstone assessment.
NumPy for AI Engineering
Required course · Premium access
Develop the array and linear-algebra fluency required to reason about tensors and vectorized AI workloads. Detailed engineering lessons with worked calculations, complete CPU labs, failure diagnosis, independent challenges and instructor capstone assessment.
PyTorch for AI Engineering
Required course · Premium access
Move from manual neural networks to production-relevant deep learning development with PyTorch. Detailed engineering lessons with worked calculations, complete CPU labs, failure diagnosis, independent challenges and instructor capstone assessment.
CPU and GPU Engineering for AI
Required course · Premium access
Understand how AI workloads use compute, memory, and parallel hardware, then benchmark real workloads. Detailed engineering lessons with worked calculations, complete CPU labs, failure diagnosis, independent challenges and instructor capstone assessment.
Computer Vision Support for AI Engineers
Required course · Premium access
Learn only the CNN concepts necessary to understand vision models and multimodal systems. Detailed engineering lessons with worked calculations, complete CPU labs, failure diagnosis, independent challenges and instructor capstone assessment.
NLP Foundations for GenAI
Required course · Premium access
Build an auditable text-to-tensor pipeline, implement miniature vocabulary and BPE algorithms, calculate embedding geometry, and debug padding, Unicode, and data leakage. Includes executable reference projects and worked solutions.
Transformers and Attention
Required course · Premium access
Implement and debug attention, multi-head layout, rotary positions, and transformer blocks using transparent NumPy experiments plus a complete optional PyTorch implementation. Includes causality tests, worked calculations, and an architecture capstone.
Hugging Face for AI Engineers
Required course · Premium access
Use Hugging Face as the practical interface to modern pretrained models, tokenizers, datasets, and inference pipelines. Includes detailed lessons, worked calculations, a complete offline reference project, debugging exercises, optional real-tool workflows and separate instructor assessment.
Local LLM Engineering
Required course · Premium access
Run, inspect, benchmark, and engineer local LLM inference workflows. Includes detailed lessons, worked calculations, a complete offline reference project, debugging exercises, optional real-tool workflows and separate instructor assessment.
Embeddings and Vector Search
Required course · Premium access
Build exact vector retrieval, measure approximation failures, implement persisted metadata-filtered CRUD, and diagnose retrieval errors with labeled evaluation. Includes metric calculations, a coarse-list ANN reference, and optional real SentenceTransformer and Qdrant workflows.
Retrieval-Augmented Generation (RAG)
Required course · Premium access
Build reliable RAG systems from ingestion through grounded generation and evaluation. Expanded engineering lessons with worked examples, runnable local practice, failure investigation and evidence-based assessment.
LangChain and LlamaIndex
Required course · Premium access
Use orchestration frameworks only after understanding the underlying LLM and retrieval primitives. Expanded engineering lessons with worked examples, runnable local practice, failure investigation and evidence-based assessment.
Function Calling and Tool Use
Required course · Premium access
Build reliable structured tool execution for LLM applications. Expanded engineering lessons with worked examples, runnable local practice, failure investigation and evidence-based assessment.
AI Agents Engineering
Required course · Premium access
Understand and build agentic systems as controlled loops around models and tools. Expanded engineering lessons with worked examples, runnable local practice, failure investigation and evidence-based assessment.
LangGraph for Stateful AI Systems
Required course · Premium access
Build explicit, stateful agent workflows with routing, loops, persistence, and human control. Expanded engineering lessons with worked examples, runnable local practice, failure investigation and evidence-based assessment.
Multi-Agent Systems
Required course · Premium access
Design multiple specialized agents only when decomposition adds measurable value. Bounded multi-worker coordination with synthetic evidence and explicit failure handling. Includes detailed lessons, worked solutions, failure injection, independent challenges and instructor assessment.
Model Context Protocol (MCP)
Required course · Premium access
Understand and build interoperable tool/resource integrations using MCP concepts. An offline protocol-contract exercise plus optional real MCP SDK client/server integration. Includes detailed lessons, worked solutions, failure injection, independent challenges and instructor assessment.
LoRA, QLoRA and PEFT
Required course · Premium access
Fine-tune open-source language models efficiently on GPU infrastructure. Actual low-rank matrix optimization plus optional real PEFT and pretrained single-GPU workflows. Includes detailed lessons, worked solutions, failure injection, independent challenges and instructor assessment.
Quantization and Inference Optimization
Required course · Premium access
Reduce memory and latency while preserving useful model quality. Actual quantization, INT4 packing, calibration and capacity calculations plus optional model comparison. Includes detailed lessons, worked solutions, failure injection, independent challenges and instructor assessment.
LLM Serving and Inference APIs
Required course · Premium access
Serve models through reliable APIs with streaming, batching, monitoring, and sensible deployment boundaries. Actual count-based generation and serving state transitions plus optional HTTP and model-runtime integration. Includes detailed lessons, worked solutions, failure injection, independent challenges and instructor assessment.
Docker, MLOps and LLMOps
Required course · Premium access
Make AI systems reproducible, observable, and maintainable. Expanded engineering lessons with complete local practice, worked solutions, failure cases and instructor assessment.
Cloud for AI Engineers
Required course · Premium access
Learn enough cloud architecture to deploy and operate AI systems without becoming a cloud specialist. Expanded engineering lessons with complete local practice, worked solutions, failure cases and instructor assessment.
AI System Design
Required course · Premium access
Design scalable, reliable AI systems and defend architecture decisions in interviews and real engineering work. Expanded engineering lessons with complete local practice, worked solutions, failure cases and instructor assessment.
AI Evaluation Engineering
Required course · Premium access
Measure whether AI systems actually work, not just whether they produce impressive demos. Expanded engineering lessons with complete local practice, worked solutions, failure cases and instructor assessment.
Flagship Production AI System
Required course · Premium access
Integrate RAG, agents, MCP, fine-tuning, serving, evaluation, and production engineering into one portfolio-grade AI system. Expanded engineering lessons with complete local practice, worked solutions, failure cases and instructor assessment.