Skip to content
K
KubeDojo
Home
Fundamentals
Linux
Cloud
AI
AI/ML
Certifications
Platform
On-Premises
Search
Ctrl
K
Cancel
Select theme
Dark
Light
Auto
GitHub
Select language
English
Українська
Menu
Home
Fundamentals
Linux
Cloud
AI
AI/ML
Certifications
Platform
On-Premises
AI/ML Engineering
Build AI Apps
AI/ML Engineering
AI/ML Hub
Prerequisites
Prerequisites
Prerequisites & Environment Setup
Home AI Workstation Fundamentals
Reproducible Python, CUDA, and ROCm Environments
Notebooks, Scripts, and Project Layouts
Build AI Apps
AI-Native Development
AI-Native Development
AI Coding Tools Landscape
Local Models for AI Coding
Configuring an Agentic Harness
Agent-First IDEs
CLI AI Coding Agents
AI-Powered Code Generation
AI-Assisted Debugging & Optimization
Building with AI Coding Assistants
Anthropic Agent SDK and Runtime Patterns
Generative AI
Generative AI
Introduction to Large Language Models
Tokenization & Text Processing
Text Generation & Sampling Strategies
Embeddings & Semantic Search
Vector Space Visualization
Reasoning Models: System 2 Thinking
Vector Search & RAG
Vector Search & RAG
Vector Databases Deep Dive
Building RAG Systems
Advanced RAG Patterns
RAG Evaluation & Optimization
Long-Context LLMs and Prompt Caching
Home-Scale RAG Systems
Frameworks & Agents
Frameworks & Agents
LangChain Fundamentals
LangChain Advanced
LangGraph for Agents
LlamaIndex
Building AI Agents
Agent Memory & Planning
Multi-Agent Systems
Model Context Protocol (MCP) for Agents
Computer Use and Browser Automation Agents
Next-Gen Agentic Frameworks
Synthesis Apps
Synthesis Apps
LLM-Native Stack: Inference and Memory on Kubernetes
Wiring the LLM App: The Orchestration Layer
Production Gates: LLM Evals in CI
Agent Observability with OpenTelemetry
Model Foundations
Deep Learning Foundations
Overview
From-Scratch Foundations (NumPy)
1.1 · NumPy, Pandas & Data Tooling
1.1.1 · Neural Network Math Warm-Up
1.1.2 · The Neuron & Perceptron from Scratch
1.1.3 · Forward Propagation in MLPs
1.1.4 · Activation Functions in Depth
1.1.5 · Loss Functions & Output Heads
1.1.6 · Backprop by Hand for Dense Nets
1.1.7 · Tiny NumPy NN Lab
1.1.8 · Computational Graphs & Scalar Autograd
PyTorch & the Training Loop
1.2 · The PyTorch Bridge
1.3 · The Training Loop
1.3.1 · Initialization & Signal Propagation
1.3.2 · Optimizers & LR Dynamics
1.3.3 · Regularization & Generalization
1.3.4 · Normalization Layers
1.3.5 · Training-Diagnostics Playbook
1.3.6 · Numerical Stability & Precision
Representations, Attention & Transformers
1.4.1 · Embeddings & Representation Learning
1.4.2 · Residual Connections & Deep Architectures
1.4.3 · Attention from Scratch
1.4.4 · The Transformer Block from Scratch
Architectures & Capstone
1.5 · CNNs & Computer Vision
1.6 · Recurrent Networks & Sequence Models
1.7 · Capstone: Train a Real Net End-to-End
Advanced Topics
1.8 · Self-Supervised Learning
1.9 · Graph Neural Networks
1.10 · Modern Transformers: RoPE & Attention Variants
Machine Learning
Machine Learning
Scikit-learn API & Pipelines
Linear & Logistic Regression with Regularization
Model Evaluation, Validation, Leakage & Calibration
Feature Engineering & Preprocessing
Decision Trees & Random Forests
XGBoost & Gradient Boosting
Naive Bayes, k-NN & SVMs
Unsupervised Learning: Clustering
Anomaly Detection & Novelty Detection
Dimensionality Reduction
Hyperparameter Optimization
Time Series Forecasting
Class Imbalance & Cost-Sensitive Learning
ML Interpretability + Failure Slicing
Probabilistic & Bayesian ML with PyMC
Recommender Systems
Conformal Prediction & Uncertainty Quantification
Fairness & Bias Auditing
Causal Inference for ML Practitioners
Reinforcement Learning
Reinforcement Learning
RL Practitioner Foundations
Offline RL & Imitation Learning
Operate & Scale
MLOps & LLMOps
MLOps & LLMOps
ML DevOps Foundations
Docker for ML
CI/CD for ML
Kubernetes for ML
Advanced Kubernetes
Experiment Tracking
Data Pipelines
ML Pipelines
Model Serving
ML Monitoring
Notebooks to Production for ML/LLMs
Small-Team Private AI Platform
AI Infrastructure
AI Infrastructure
Cloud AI Services
AIOps
High-Performance LLM Inference: vLLM and sglang
Local Inference Stack for Learners
Home AI Operations and Cost Model
GPU Memory Hierarchy and Bandwidth Math for LLM Inference
Production-Tier LLM Inference Engines: Decision Framework
Benchmarking LLM Inference: TTFT, TPOT, and Workload-Aware Load Shaping
Advanced GenAI & Safety
Advanced GenAI & Safety
Fine-tuning LLMs
LoRA & Parameter-Efficient Fine-tuning
Diffusion Models
RLHF & Alignment
Advanced Generation Techniques
LLM Evaluation
AI Red Teaming
AI Safety & Alignment
Modern PEFT: DoRA and PiSSA
Single-GPU Local Fine-Tuning
Multi-GPU and Home-Lab Fine-Tuning
Reasoning-Model RL: GRPO, RLVR, and DeepSeek-R1
Multimodal AI
Multimodal AI
Voice & Audio AI
Vision AI
Video AI
Multimodal-First AI Design
Reference
Bridges to Other Tracks
AI/ML Engineering Bridges
From AI Builder to AI Platform Engineer
From Home Lab AI to Private AI Infrastructure
Appendix A: History of AI/ML
Appendix A: History of AI/ML
History of AI & Machine Learning
GitHub
Select theme
Dark
Light
Auto
Select language
English
Українська
Frameworks & Agents
AI/ML Engineering Track
| Phase 4
Modules
Section titled “Modules”
#
Module
1.1
LangChain Fundamentals
1.2
LangChain Advanced
1.3
LangGraph for Agents
1.4
LlamaIndex
1.5
Building AI Agents
1.6
Agent Memory & Planning
1.7
Multi-Agent Systems
1.8
Model Context Protocol (MCP) for Agents
1.9
Computer Use and Browser Automation Agents
1.10
Next-Gen Agentic Frameworks