Skip to content
LIVE Agentic AI Workshop · 7 NovView workshop →
NETSETOS
My LearningJoin workshop

Explore Netsetos

My Learning
Join workshopAll courses →
Contact Support · info@netsetos.com
top of page

GenAI Engineering: Build, Scale & Deploy AI Systems

GenAI Engineering cover: documents, an embeddings grid, a model chip, three replicas and a monitoring chart

Group Discussion

This program is connected to a group. You’ll be added once you join the program.

Netsetos Group

Netsetos Group

Private484 Members

Master production-grade Generative AI engineering across 18 modules and 124 hands-on steps. Cover transformer architecture, embeddings, vector databases, RAG pipelines, fine-tuning (LoRA/QLoRA), AI agents, LLMOps, and deployment on GCP. Lessons ship with runnable code and self-check quizzes, plus practice labs — built for working software engineers by a Technical Architect with 15+ years of industry experience.

Course syllabus

  1. Module 00 · Python Prerequisites
    1. Lesson 0.1 - Python for GenAI
  2. Module 01 · Math Prerequisites
    1. Lesson 1.1 - Math Foundations 1: The Basics
    2. Lesson 1.2 - Math Foundations 2: How Models Learn
    3. Lesson 1.3 - Math Foundations 3: Transformer Architecture
    4. Lesson 1.4 - Math Foundations 4: Transformer Plumbing
    5. Lesson 1.5 - ML Patterns
    6. Lesson 1.6 - K-Means Clustering
    7. Lesson 1.7 - Ensemble Methods
    8. Lesson 1.8 - Probability & Statistics for AI Engineers
  3. Module 02 · Data Prerequisites
    1. Lesson 2.1 - Data Wrangling for GenAI
    2. Lesson 2.2 - SQL for GenAI Engineers
  4. Module 03 · GenAI Foundations
    1. Lesson 3.1 - What Is GenAI
    2. Lesson 3.2 - History of GenAI
  5. Module 04 · Model Architecture
    1. Lesson 4.1 - Tokenization & Embeddings
    2. Lesson 4.2 - Transformer from Scratch
    3. Lesson 4.3 - BERT & Encoder Models
    4. Lesson 4.4 - GPT & Decoder Models
    5. Lesson 4.5 - Pre-Training at Scale
  6. Module 05 · Prompt Engineering
    1. Lesson 5.1 - Prompting Fundamentals
    2. Lesson 5.2 - Few-Shot & In-Context
    3. Lesson 5.3 - Advanced Reasoning
    4. Lesson 5.4 - Context Engineering
    5. Lesson 5.5 - Structured Output & Tool Use
    6. Lesson 5.6 - Prompt Optimization & DSPy
    7. Lesson 5.7 - Adversarial Prompting & Defenses
  7. Module 06 · Image & Multimodal Generation
    1. Lesson 6.1 - Diffusion Models
    2. Lesson 6.2 - Stable Diffusion Ecosystem
    3. Lesson 6.3 - Controlled Generation
    4. Lesson 6.4 - ViT & CLIP
    5. Lesson 6.5 - Multimodal Models
    6. Lesson 6.6 - Video & 3D Generation
    7. Lesson 6.7 - Voice AI: STT & TTS
  8. Module 07 · LLM API Engineering
    1. Lesson 7.1 - Multi-Provider API
    2. Lesson 7.2 - Streaming & Realtime
    3. Lesson 7.3 - Cost Engineering
    4. Lesson 7.4 - AI Chat with FastAPI
    5. Lesson 7.5 - Function Calling & Tools
    6. Lesson 7.6 - Observability with Langfuse
  9. Module 08 · RAG Systems
    1. Lesson 8.1 - RAG Fundamentals
    2. Lesson 8.2 - Document Processing
    3. Lesson 8.3 - Embeddings & Vector Stores
    4. Lesson 8.4 - Advanced Retrieval
    5. Lesson 8.5 - RAG with LangChain
    6. Lesson 8.6 - RAG with LlamaIndex
    7. Lesson 8.7 - GraphRAG
    8. Lesson 8.8 - Conversational RAG
    9. Lesson 8.9 - Multimodal RAG
    10. Lesson 8.10 - Agentic RAG
    11. Lesson 8.11 - RAG Evaluation & RAGAS
  10. Module 09 · Fine-Tuning
    1. Lesson 9.1 - When to Fine-Tune
    2. Lesson 9.2 - Data Preparation
    3. Lesson 9.3 - Fine-Tuning with Vertex AI
    4. Lesson 9.4 - Open-Source Fine-Tuning
    5. Lesson 9.5 - LoRA & QLoRA Adapters
    6. Lesson 9.6 - Eval, Merge & Deploy
  11. Module 10 · Tool Use & MCP
    1. Lesson 10.1 - Function Calling for MCP
    2. Lesson 10.2 - Designing Tool Schemas
    3. Lesson 10.3 - Multi-Tool Orchestration
    4. Lesson 10.4 - What Is MCP
    5. Lesson 10.5 - Building MCP Servers
    6. Lesson 10.6 - Remote MCP on Cloud Run
    7. Lesson 10.7 - Production MCP Patterns
  12. Module 11 · AI Agents
    1. Lesson 11.1 - Agent Fundamentals
    2. Lesson 11.2 - Agent Architectures
    3. Lesson 11.3 - LangGraph Deep Dive
    4. Lesson 11.4 - Memory Systems
    5. Lesson 11.5 - Multi-Agent: CrewAI & Agno
    6. Lesson 11.6 - Computer Use Agents
    7. Lesson 11.7 - Coding Agents
    8. Lesson 11.8 - Deep Research Agents
    9. Lesson 11.9 - Long-Running Async Agents
    10. Lesson 11.10 - Human-in-the-Loop
    11. Lesson 11.11 - Agent Eval & Security
  13. Module 12a · Guardrails
    1. 12.1 - The Guardrail Threat Model
    2. 12.2 - The Five Rails: Where Guardrails Live
    3. 12.3 - Input Rails: Injection & Jailbreak Detection
    4. 12.4 - PII Detection & Redaction Pipelines
    5. 12.5 - Output Rails: Validators, Moderation & Groundedness
    6. 12.6 - Execution Rails: Guardrails for Agents & Tool Calls
  14. Module 12b · Production Deployment
    1. Lesson 12.1 - Architecture Patterns
    2. Lesson 12.2 - Designing Reliability
    3. Lesson 12.3 - AI Gateway Pattern
    4. Lesson 12.4 - Caching Strategies
    5. Lesson 12.5 - Docker & Containerization
    6. Lesson 12.6 - CI/CD for AI Apps
    7. Lesson 12.7 - Scaling AI Apps
    8. Lesson 12.8 - Monitoring & Observability
    9. Lesson 12.9 - Production Incidents
    10. Lesson 12.10 - AI-Powered UX
  15. Module 13 · Cost & Performance
    1. Lesson 13.1 - AI App Costs
    2. Lesson 13.2 - Prompt Optimization
    3. Lesson 13.3 - Model Selection & Routing
    4. Lesson 13.4 - Latency Optimization
    5. Lesson 13.5 - Self-Hosting with Ollama
    6. Lesson 13.6 - vLLM & GKE Production
  16. Module 14 · LLMOps
    1. Lesson 14.1 - LLMOps Foundations
    2. Lesson 14.2 - Prompt Versioning & A/B Testing
    3. Lesson 14.3 - Observability & Evaluation
    4. Lesson 14.5 - Serving & Cost Optimization
    5. Lesson 14.6 - LLMOps Capstone
  17. Module 15 · Ethics & Responsible AI
    1. Lesson 15.1 - Bias Detection
    2. Lesson 15.2 - Explainable AI
    3. Lesson 15.3 - Copyright & IP
    4. Lesson 15.4 - Privacy & Data Protection
    5. Lesson 15.5 - Deepfakes & Misuse
    6. Lesson 15.6 - Regulatory Landscape
    7. Lesson 15.7 - AI Governance Frameworks
  18. Module 16 · Industry Applications
    1. Lesson 16.1 - GenAI in Healthcare
    2. Lesson 16.4 - Software Engineering
    3. Lesson 16.5 - GenAI for Non-Developer Roles
  19. Practice Exercise Lab
    1. Module 0 - Python & Math Foundations
    2. Module 1 - Classical ML & Stats
    3. Module 1 - Introduction To GenAI
    4. Module 2 - LLMs Deep Dive
    5. Module 3 - Prompt Engineering & Context Design
    6. Module 4 - Image, Vision & Multimodal AI
    7. Module 5 - Production Applications with GenAI APIs
    8. Module 6 - Retrieval Augmented Generation
    9. Module 7 - Fine Tuning LLMs
    10. Module 8 - MCP, Tool Orchestration & Function Calling
    11. Module 9 - AI Agents & Autonomous Systems
    12. Module 10 - AI System Architecture & Prod Development
    13. Module 11 - Cost Optimization & Efficiency
    14. Module 12 - Ethics, Safety, Governance & Explainability

223 enrolments, as of Oct 2026

Questions about this course

Is it really free?

Yes. There is no fee and no card is needed. You join with a free site account so your progress is saved.

How long does it take?

It is self-paced, so it depends on you. There are 124 steps: 110 lessons across 18 modules, plus a 14-step practice lab.

Is there a certificate?

Yes. You get a certificate when you complete all 124 steps.

Is this a live course?

No. It is self-paced: you work through the steps on your own schedule. Netsetos runs live teaching separately, as the Agentic AI cohort on Zoom.

bottom of page