← All posts
Course · 30 lessons
AI Intermediate: Infrastructure & Agentic Systems
From containers to autonomous agents
A hands-on 30-day course for engineers who want to run AI in production: containers, Kubernetes, networking and security, then MLOps and enterprise agents, one lesson a day with animated diagrams.
Starting soon: 30 lessons, one a day.
Week 1 · Bare-Metal Infrastructure & Advanced Containerization
- Day 1The AI Infrastructure Shift: Why the Model is Only 10% of the Production SystemComing soon
- Day 2Advanced Docker for AI: Multi-Stage Builds for Heavy Python RuntimesComing soon
- Day 3Hardware Acceleration in Docker: Configuring Resource Passthrough for Constrained HardwareComing soon
- Day 4Optimizing Model Weights: Quantization Basics (GGUF, AWQ) for Efficient InferenceComing soon
- Day 5Local AI Runtimes: Deploying Ollama and vLLM for Bare-Metal ExecutionComing soon
- Day 6Containerizing AI Microservices: Building and Packaging APIs with FastAPIComing soon
- Day 7Docker Compose: Architecting a Multi-Container Database and Inference Stack LocallyComing soon
Week 2 · Kubernetes Foundation for MLOps
- Day 8K3d & Lightweight Kubernetes: Running Multi-Node Clusters on 16GB of RAMComing soon
- Day 9Kubernetes Core for Machine Learning: Pods, Deployments, and Headless ServicesComing soon
- Day 10Persistent Volumes (PV/PVC): Managing Heavy Model Weights and Vector StoresComing soon
- Day 11StatefulSets for Vector Databases: Deploying Milvus or Qdrant in KubernetesComing soon
- Day 12Auto-Scaling AI Inference: Using Horizontal Pod Autoscalers (HPA) for Spiky API TrafficComing soon
- Day 13Helm Charts: Packaging, Versioning, and Updating AI DeploymentsComing soon
- Day 14Week 2 Capstone: Deploying a Highly Available Local AI Application on K3dComing soon
Week 3 · High-Performance Networking & Security Mesh
- Day 15AI Network Bottlenecks: Transitioning from iptables to eBPFComing soon
- Day 16Cilium & eBPF: Sub-Millisecond Routing for Heavy AI MicroservicesComing soon
- Day 17Service Mesh 101: Installing Istio over Your Local ClusterComing soon
- Day 18Envoy Proxy as an AI Gateway: Load Balancing and Terminating LLM PromptsComing soon
- Day 19Zero-Trust mTLS: Encrypting Traffic Between Autonomous AgentsComing soon
- Day 20API Rate Limiting & Egress Control: Preventing Agents from Exfiltrating DataComing soon
- Day 21Distributed Tracing: Debugging Agent Workflows with Jaeger and OpenTelemetryComing soon
Week 4 · Enterprise Agents & CI/CD Workflows
- Day 22Introduction to MLOps: Bridging AI Development with Continuous IntegrationComing soon
- Day 23GitOps with ArgoCD: Automated, Self-Healing AI DeploymentsComing soon
- Day 24Building Ephemeral AI Sandboxes: Secure Execution Environments for Agent CodeComing soon
- Day 25Multi-Agent Orchestration Frameworks: Exploring Mastra, LangGraph, and CrewAIComing soon
- Day 26Tool-Calling in Production: Connecting Agents Securely to Internal DatabasesComing soon
- Day 27MLOps Guardrails: Evaluating Agents and Preventing Hallucinations in Real-TimeComing soon
- Day 28Continuous Training Pipelines: Connecting Data Ingestion to Automated Model RetrainingComing soon
- Day 29Managing Technical Debt and Infrastructure Drift in Enterprise AIComing soon
- Day 30The AI-Native Platform: Scaling from a Sandbox Environment to Global Cloud ArchitectureComing soon