AI Engineer Bootcamp

Set up your environment and core mental models.

1. Modern Python Toolchain with uv
2. Async Python: asyncio Foundations
3. Advanced Async: Concurrency Control
4. Resilience: Retry, Circuit Breaker, Fallback
5. Type Systems and Pydantic for AI
6. Pydantic Advanced: Validators & Schemas
7. Generators, Iterators & Streaming
8. Decorators, Metaclasses & Metaprogramming
9. Error Handling & Logging for AI Systems
10. Data Structures & Algorithms for AI
11. Testing AI Systems: Unit & Integration
12. Testing AI Systems: Evaluation Harnesses
13. Python Packaging & Project Structure
14. Docker for AI Applications
15. Functional Programming Patterns
16. Performance Profiling & Optimization
17. CLI Tools & Developer Experience

Understand how LLMs work and how to call them.

1. Neural Network Foundations for AI Engineers
2. The Transformer Architecture from First Principles
3. Attention Mechanisms Deep Dive
4. Tokenization: BPE, SentencePiece, and Cost Implications
5. Context Windows: Engineering for Limited Space
6. Sampling, Temperature, and Generation Control
7. Model Architectures: Decoder-Only, Encoder-Decoder, and MoE
8. Pre-Training, Fine-Tuning, and RLHF Overview
9. Scaling Laws and Model Selection Economics
10. Model Selection and Intelligent Routing
11. Multimodal Understanding: Vision
12. Multimodal Understanding (Documents, Audio, and Video)
13. Inference Optimization: KV Cache, Batching, and Quantization
14. Emergent Capabilities and Reasoning Patterns
15. Constitutional AI, Safety, and Alignment
16. The LLM Landscape: Comparing Production Models
17. Research Literacy (Reading AI Papers)

Master prompting for reliable outputs.

1. The Anthropic Claude API: Messages and Streaming
2. Claude Advanced Features: Caching, Extended Thinking, Batch
3. Tool Use and Function Calling: Fundamentals
4. Tool Use Advanced (Chaining, Confirmation, and Parallel)
5. Structured Output and Schema Validation
6. The OpenAI API: GPT-6 and Beyond
7. Google Gemini and Other Providers
8. Cross-Provider Abstraction with LiteLLM
9. Building a Production API Client Library
10. Streaming Architecture: SSE, WebSockets, and HTTP/2
11. Batch Processing and Offline Workloads
12. Rate Limiting and Quota Management
13. Cost Tracking and Budget Controls
14. API Security (Keys, OAuth, and Secrets Management)
15. API Versioning and Migration Strategies
16. Logging, Tracing, and Debugging API Calls
17. Building API Mocks and Test Doubles

Ground models in your own data.

1. System Prompt Architecture
2. Prompt Templates and Composition
3. Chain-of-Thought and Step-by-Step Reasoning
4. Extended Thinking and Scratchpad Patterns
5. Tree-of-Thought and Advanced Reasoning
6. Few-Shot Learning and Example Selection
7. Output Format Control and Structured Prompting
8. Persona Design and Role Prompting
9. Prompt Chaining and Multi-Step Workflows
10. Prompt Injection Defense (Attack Taxonomy)
11. Prompt Injection Defense (Layered Protection)
12. Prompt Optimization and Cost Reduction
13. Prompt Versioning, Testing, and CI/CD
14. Domain-Specific Prompt Engineering
15. Prompt Engineering for Agents
16. Multilingual and Cross-Cultural Prompting
17. Prompt Engineering Evaluation and Continuous Improvement

Build agents that plan and act.

1. RAG Architecture and Theory
2. Building a RAG Pipeline from Scratch
3. Chunking Strategies and Document Processing
4. Embedding Models (Selection and Evaluation)
5. Fine-Tuning Embeddings for Domain Performance
6. Vector Databases (Pinecone and Managed Services)
7. Vector Databases (pgvector and Self-Hosted Options)
8. Retrieval Strategies (Hybrid Search and Re-Ranking)
9. Advanced Retrieval (Agentic and Self-RAG)
10. Graph RAG (Knowledge Graphs Meet Vector Search)
11. RAG Evaluation with RAGAS
12. RAG Evaluation (Beyond RAGAS)
13. Document Ingestion Pipelines
14. Multi-Tenant RAG Architecture
15. RAG Performance Optimization
16. RAG with Frameworks (LlamaIndex)
17. RAG Production Deployment

Give models real capabilities.

1. Conversation Design and Message Management
2. Short-Term Memory (Within-Conversation Context)
3. Long-Term Memory (Cross-Session Persistence)
4. Episodic and Semantic Memory Systems
5. Streaming Architectures for Real-Time AI
6. Building AI-Powered APIs with FastAPI
7. Session Management and Conversation Routing
8. Conversation Analytics and Feedback Systems
9. Multi-Channel Conversational AI
10. Conversation Safety and Moderation
11. Chatbot Personality and Tone Management
12. Human Handoff and Hybrid Support
13. Conversation Testing and Quality Assurance
14. Conversation Summarization and Handoff Documents
15. Building a Production Chat Application
16. Conversation Design Patterns Library
17. Advanced Memory (Knowledge Graphs for Conversation Context)

Connect agents to systems with MCP.

1. The AI Testing Pyramid
2. Building Evaluation Datasets
3. LLM-as-Judge Evaluation
4. Automated Evaluation Frameworks: RAGAS, DeepEval, Promptfoo
5. Statistical Methods for AI Evaluation
6. Benchmarking and Performance
7. Red-Team Testing for AI Safety
8. Regression Testing and Quality Gates
9. Production Monitoring
10. Evaluating Agent Systems
11. Evaluating RAG End-to-End
12. Human Evaluation Workflows
13. Testing for Bias and Fairness
14. Cost-Quality Tradeoff Analysis
15. Building an Evaluation Platform
16. Evaluation-Driven Development
17. Testing in Production

Coordinate multiple agents.

1. What is an Agent: Definitions and Taxonomy
2. The Agent Loop: ReAct Pattern
3. Plan-and-Execute Agents
4. Reflexion and Self-Improving Agents
5. Tool Design for Agents
6. Tool Composition and Chaining
7. Agent Memory and State Management
8. Agent Guardrails and Safety
9. Error Handling, Fallbacks, and Reliability
10. Human-in-the-Loop Patterns
11. Agent Observability and Debugging
12. Agent Evaluation and Benchmarking
13. Agent Architectures for Common Use Cases
14. Agent Design Anti-Patterns
15. Building Agent Frameworks
16. Long-Running and Persistent Agents
17. Agent Patterns Synthesis and Selection Guide

Customize models to your domain.

1. SDK Architecture and Setup
2. Built-in Tools Deep Dive
3. Custom Tool Development
4. Tool Orchestration and Advanced Patterns
5. Skills: Reusable Agent Capabilities
6. Skill Design Patterns and Best Practices
7. Subagents: Parallel and Specialized Execution
8. Multi-Agent Patterns with the SDK
9. Agent SDK Configuration and Optimization
10. Hooks and Middleware
11. Testing Agent SDK Applications
12. TypeScript Implementation
13. Production Deployment
14. Security and Sandboxing
15. Building Plugins and Extensions
16. Managed Agents and Cloud Deployment
17. SDK Capstone: Full-Stack Agent Application

Store and search vectors at scale.

1. MCP Architecture and Specification
2. Building MCP Servers in Python: Fundamentals
3. MCP Server Advanced Patterns: Auth and Middleware
4. Building MCP Servers in TypeScript
5. MCP Resources and Data Access
6. MCP Prompts and Template Systems
7. MCP Transport: stdio for Local
8. MCP Transport: Streamable HTTP for Remote
9. MCP Client Implementation
10. MCP Server Testing and Quality
11. MCP Registry, Discovery, and Ecosystem
12. Integrating MCP with Agent Frameworks
13. Building Real-World MCP Integrations
14. MCP Security and Access Control
15. MCP Versioning and Evolution
16. MCP in Production: Operations and Monitoring
17. MCP Capstone: Enterprise Integration Platform

Build safe, secure AI systems.

1. Multi-Agent Orchestration Patterns
2. LangGraph (Stateful Agent Workflows)
3. Agent Communication Protocols
4. Designing Agent Teams and Roles
5. Shared State and Memory in Multi-Agent Systems
6. Dynamic Agent Spawning and Scaling
7. Observability and Debugging Multi-Agent Systems
8. CrewAI (Role-Based Agent Teams)
9. Microsoft Agent Framework (AutoGen's Successor): Conversational Multi-Agent Systems
10. Framework Comparison: LangGraph vs. CrewAI vs. Microsoft Agent Framework
11. Error Handling and Recovery in Multi-Agent Systems
12. Cost Optimization for Multi-Agent Systems
13. Security and Isolation in Multi-Agent Systems
14. Workflow Patterns for Enterprise AI
15. n8n Integration for External Orchestration
16. Testing Strategies for Multi-Agent Systems
17. Multi-Agent Capstone (Build a Complete Autonomous Research System)

Measure and trust your system.

1. AI System Architecture Patterns
2. Authentication and Authorization for AI APIs
3. Multi-Tenancy for AI Applications
4. Database Design for AI Applications
5. Message Queues and Async Processing
6. Caching Architecture for AI
7. API Design for AI Features
8. Containerization and Docker for AI
9. CI/CD for AI Applications
10. Deployment Platforms
11. Monitoring and Observability for AI
12. Logging and Tracing for AI Systems
13. Load Testing and Capacity Planning
14. Feature Flags and Progressive Rollout
15. Infrastructure as Code for AI
16. Disaster Recovery and Business Continuity
17. Enterprise Architecture Capstone

Ship AI to production.

1. Prompt Injection Attacks: Direct Injection
2. Prompt Injection: Indirect/Second-Order Attacks
3. Jailbreak Defense Strategies
4. PII Detection and Redaction
5. Data Leakage Prevention
6. Input Sanitization Pipelines
7. Output Filtering and Guardrails
8. Rate Limiting for AI Systems
9. Abuse Detection and Prevention
10. Role-Based Access Control for AI
11. Audit Logging and Compliance Trails
12. SOC 2 Compliance for AI Systems
13. HIPAA Considerations for AI
14. GDPR and Data Privacy
15. Threat Modeling for AI Systems
16. Red Teaming AI Systems
17. Secure Development Lifecycle for AI

See what your system is doing.

1. Token Economics and Cost Modeling
2. Provider-Native Caching: Prompt Caching
3. Application-Level Caching
4. Intelligent Routing for Cost Optimization
5. Prompt Optimization for Token Efficiency
6. Batch Processing for Cost Reduction
7. Cost Monitoring and Budget Controls
8. Usage-Based Billing Integration
9. Cost Forecasting and Capacity Planning
10. Multi-Model Cost Strategy
11. Output Optimization: Length, Format, and Efficiency
12. Cost Attribution and Chargebacks
13. Open Source and Self-Hosted Cost Models
14. LLMOps (Operational Cost Reduction)
15. Cost Communication and ROI Justification
16. Cost Optimization Case Studies
17. Cost Management Capstone

Control spend without losing quality.

1. The Customization Spectrum: When to Fine-Tune
2. Training Data Collection Strategies
3. Data Annotation and Quality Assurance
4. Dataset Preparation and Format Conversion
5. LoRA (Low-Rank Adaptation Theory and Practice)
6. QLoRA (Quantized Fine-Tuning on Consumer Hardware)
7. Training Configuration and Hyperparameter Tuning
8. Evaluating Fine-Tuned Models
9. DPO: Direct Preference Optimization
10. RLHF Overview and When to Use It
11. Model Distillation: Training Smaller from Larger
12. Quantization for Deployment
13. Model Serving with vLLM
14. Model Serving with Ollama for Local Deployment
15. Model Version Management and A/B Testing
16. Fine-Tuning Pipeline Automation
17. Fine-Tuning Decision Guide and Best Practices

Design for the enterprise.

1. Voice AI Architecture Overview
2. Speech-to-Text with Deepgram
3. STT with Whisper & Alternatives
4. Text-to-Speech with ElevenLabs
5. TTS Alternatives & Voice Design
6. Building Real-Time Voice Agents
7. Voice Agent Session Management
8. Voice Agent Testing & Quality
9. Computer Use -- Claude Desktop Automation
10. Browser Automation with AI Agents
11. Image Generation & AI Visual Content
12. Document Understanding -- OCR & Structured Extraction
13. Video Understanding & Processing
14. Multimodal Pipeline Design
15. Accessibility & Inclusive AI Design
16. Voice & Multimodal Security
17. Multimodal Capstone -- Full-Stack Voice Application

Turn capabilities into products.

1. Knowledge Graphs (Neo4j Fundamentals)
2. LLM-Powered Knowledge Graph Construction
3. Graph RAG: Combining Graphs with Vector Search
4. Hybrid Search & Multi-Source Retrieval
5. Document Processing at Enterprise Scale
6. Agentic RAG: Query Analysis & Strategy Selection
7. Agentic RAG: Iterative Retrieval & Self-Assessment
8. Knowledge Base Maintenance & Freshness
9. Conversational Knowledge Systems
10. Citation & Source Attribution Systems
11. Semantic Search & Discovery
12. Multi-Language Knowledge Systems
13. Knowledge System Evaluation
14. Knowledge System Security & Access Control
15. Knowledge System Performance Optimization
16. Enterprise Knowledge Architecture
17. Knowledge Systems Capstone

Learn from real implementations.

1. The VFR Framework (AI Product Strategy)
2. Core AI Feature Design Patterns
3. Multi-Tenant AI SaaS Architecture
4. User Onboarding for AI Products
5. UX Design for AI Features
6. AI-Powered Search and Discovery
7. Analytics for AI Products
8. A/B Testing AI Features
9. AI Product Pricing and Monetization
10. Scaling AI Products: 10 to 10,000 Users
11. AI Consulting Methodology
12. Client Discovery and Requirements Gathering

Build a complete agentic system.

1. The Open Source LLM Landscape
2. Running Local LLMs with Ollama
3. Production Inference with vLLM
4. llama.cpp & CPU Inference
5. Hardware Planning for Local Inference
6. Hybrid Cloud-Local Architectures
7. Model Fine-Tuning & Local Training
8. Model Serving Best Practices
9. Edge AI & Embedded Deployment
10. Model Registries & Version Management
11. Open Source Model Security
12. Community Models & Specialized Open Source
13. Running Open Source Embedding Models Locally
14. Building Custom Inference APIs
15. Cost Comparison -- Self-Hosted vs API
16. Monitoring & Operations for Self-Hosted Models
17. Open Source AI Capstone -- Hybrid Deployment

Launch your AI engineering career.

1. Capstone Planning (Problem Selection)
2. Architecture Design & Technical Planning
3. Development Environment & Project Setup
4. Core System Implementation (Database & API)
5. AI Integration: Core Intelligence
6. RAG & Knowledge Integration
7. Agent Features: Autonomous Capabilities
8. Advanced Features: Differentiators
9. Frontend & User Experience
10. Security & Compliance Implementation
11. Cost Optimization & Performance Tuning
12. Testing & Evaluation Suite
13. Production Deployment
14. Load Testing & Operational Readiness
15. Documentation & Technical Writing
16. Presentation & Demo Preparation
17. Capstone Presentation & Portfolio

Prove your skills and certify.

1. Building AI Teams: Hiring & Structure
2. AI Team Culture & Development
3. Staying Current in AI
4. AI Strategy for Organizations
5. AI Project Management
6. The Business of AI Engineering
7. AI Consulting: Client Relationships
8. AI Ethics & Responsible Development
9. AI Governance & Risk Management
10. AI Industry Analysis & Market Positioning
11. Building an AI Portfolio & Personal Brand
12. Teaching & Mentoring in AI
13. AI Career Planning & Growth
14. The Future of AI Engineering
15. Open Source Contribution Strategy
16. AI Regulation & Policy Literacy
17. Course Synthesis & Graduation