Training programme overview
Deploy reliable AI workloads: containers, Kubernetes for GPU workloads, serverless approaches, vLLM model serving, autoscaling, reliability practices and levers to control cost and performance in production.
An advanced track focused on infrastructure required for production AI services, from containerization to GPU orchestration.
The Kubernetes module covers GPU workload management, scheduling constraints and integration with storage and networking.
Model serving lessons present approaches such as vLLM and serverless configurations suited to inference workloads.
Finally, the course examines reliability practices, rollout strategies and optimization techniques to manage cost and availability.
Training · Advanced
Courses included in this training programme
Infrastructure Foundations
Overview of infrastructure fundamentals for deploying AI models: CPU vs GPU trade-offs, containerizing applications, async inference patterns and secrets/config promotion. Focus on architectural choices and operational consequences.
4 lessons · 20 activities · 0 exercises · 3 videos
Kubernetes and GPU Workloads
Deep dive into Kubernetes for GPU workloads: Kubernetes primitives for AI services, GPU scheduling, NVIDIA GPU Operator and GPU telemetry/failure modes. Practical guidance for running GPU clusters in production.
4 lessons · 20 activities · 0 exercises · 3 videos
Model Serving with vLLM
Introduction to model serving with vLLM: serving architecture patterns, OpenAI-compatible endpoints, batching and KV-cache optimizations, plus routing and autoscaling strategies for production stacks.
4 lessons · 20 activities · 0 exercises · 3 videos
Reliability and Release
Focus on reliability and release for AI services: health checks and load testing, blue/green and canary release strategies, provider fallback and a production readiness review process.
4 lessons · 20 activities · 0 exercises · 3 videos
Access the platform
Open the catalogue to review course details, access conditions, and your personal progress. Sign in.