Platform Engineering & AI Architecture
Master Platform Engineering, AI Systems, LLMs, and MLOps with comprehensive bootcamps, courses, and hands-on labs
All Bootcamps (3)
AI Platform Engineering Bootcamp
An 8-week intensive program designed to transition Platform Engineers into AI Platform Engineering and LLMOps roles. Build production-ready AI systems using LLMs, RAG, agents, and MLOps practices on Kubernetes infrastructure.
Platform Engineering Bootcamp
Comprehensive 21-week bootcamp equipping engineers with essential and advanced Platform Engineering and DevOps skills using industry-standard tools and best practices.
HashiCorp Vault Security Bootcamp
Comprehensive 3-week bootcamp mastering HashiCorp Vault from fundamentals to advanced operations. Learn secrets management, Kubernetes integration, enterprise deployment, and prepare for certification.
All Courses (46)
AI Agents and Agentic Workflows
Build autonomous AI agents that can reason, plan, and execute complex tasks. Master LangChain, LangGraph, and MCP for creating Platform Engineering assistants that query Kubernetes clusters with safety guardrails. Transform your RAG-powered assistant into an agent that can actually take actions.
AI Foundations for Infrastructure Engineers
Bridge the gap between traditional infrastructure and AI systems. This course provides just enough ML theory to understand what you're deploying, without diving into academic machine learning. By the end, you will have run your first local LLMs and understood their resource requirements.
AI Observability and LLMOps
Master observability for AI systems with Prometheus metrics, Grafana dashboards, and distributed tracing. Implement LLM evaluation frameworks, production guardrails for safety, and drift detection pipelines. Build the monitoring infrastructure that keeps AI systems reliable in production.
Enterprise AI and Capstone Project
Complete your AI Infrastructure journey by mastering enterprise-grade security, governance, and compliance. Then bring everything together in a comprehensive capstone project: build a production-ready Platform Engineering Assistant that combines RAG, agents, observability, and security. This is the culmination of everything you've learned.
LLM Integration and API Patterns
Master the practical skills of integrating LLMs into applications. Focus on API patterns, structured outputs, resilience, and cost-effective integrations. Build a production-ready API layer that routes between local and cloud models, handles failures gracefully, and tracks costs.
ML Infrastructure and Experiment Tracking
Master the infrastructure behind machine learning workflows. Implement experiment tracking, model versioning, and ML pipeline orchestration using GitOps principles. Learn to track prompt experiments, compare strategies, and version your AI systems for continuous improvement.
Model Serving and Kubernetes for ML
Master model serving infrastructure for production AI systems. Learn GPU scheduling concepts, Kubernetes resource management for ML workloads, KServe for serverless model inference, and production deployment patterns including canary and blue-green strategies.
RAG Architectures and Vector Databases
Build enterprise-grade Retrieval-Augmented Generation systems. Connect LLMs to organizational knowledge bases, implement semantic search, and optimize retrieval pipelines. By the end, you'll have built the ability to teach your assistant about your organization by connecting it to your knowledge base.
CNPA Certification Prep: Cloud Native Platform Engineering Associate
Start your platform engineering career and prepare for the CNCF Certified Cloud Native Platform Engineering Associate (CNPA) exam - no prior platform engineering experience required
All Labs (273)
Advanced RAG Patterns
Implement reranking and hybrid search to significantly improve RAG retrieval quality with measurable metrics.
AI Authentication and Authorization
Implement authentication and authorization patterns for AI systems including API key management, OAuth 2.0, multi-tenant isolation, and audit logging.
Bedrock Multi-Model Integration
Build a multi-model service using AWS Bedrock to access Claude, compare it with direct API calls, and implement intelligent provider fallback.
Bedrock + Lambda Serverless AI
Build a serverless AI endpoint using AWS Lambda and Bedrock, exposed through API Gateway for production use.
Canary Model Deployment
Implement canary deployments for safe ML model updates using KServe.
Capstone Part 2: Agent Development
Build a Platform Engineering Assistant agent with LangChain tools, safety guardrails, and RAG integration.
Capstone Part 3: Production Infrastructure
Deploy the Platform Engineering Assistant to Kubernetes with production-grade infrastructure: Helm charts, resource management, health checks, and autoscaling.
Capstone Part 4: Observability and Security
Complete the Platform Engineering Assistant with production observability and security: Prometheus metrics, Grafana dashboards, Vault secrets integration, and request logging.
Capstone Part 1: RAG Foundation
Build the RAG foundation for the Platform Engineering Assistant. Deploy ChromaDB, ingest Kubernetes documentation, create embeddings, and implement a retrieval API.
Ready to Start Learning?
Join thousands of students mastering DevOps and Platform Engineering
View Pricing Plans