LLMs on the Cloud

Bedrock, Azure AI Foundry, Vertex AI, GPUs, cost models, reference architectures

• Managed APIs vs Self-Hosting — The consumption spectrum from serverless tokens to your own GPU fleet: what you inherit at each step, and the drivers that actually decide it. (3 lessons, 40 min)
• Bedrock, Azure AI Foundry, Vertex AI — The three managed model platforms share one shape — catalog, serverless, provisioned, customization, guardrails. The tour, verified against the docs. (3 lessons, 50 min)
• Self-Hosting on EKS, AKS, GKE — Running your own serving stack on managed Kubernetes: the GPU node reality, the engine deployment, and the day-2 work nobody budgets. (4 lessons, 50 min)
• GPUs and Accelerators — The hardware menu across the three clouds — what the specs actually mean for LLM serving, and the custom-silicon alternatives. (4 lessons, 45 min)
• Cost Modeling — Three meters — per-token, provisioned units, GPU-hours — and the break-even thinking that decides between them, with utilization as the hidden variable. (4 lessons, 45 min)
• Reference Architectures — Three architectures that cover most LLM systems — the managed-API app, the RAG stack, the self-hosted cluster — drawn end to end, per cloud. (4 lessons, 50 min)
• In Production: Multi-Region, Quota, and Failover — The domain’s production capstone: quotas as an architectural force, cross-region serving mechanisms, and failover patterns that survive contact with reality. (3 lessons, 40 min)