**Why do 87% of AI models never reach production? It's not the AI - it's the infrastructure underneath.**
In this deep dive episode of Platform Engineering Playbook, we tackle the critical challenge of building cloud-native platforms that can actually support AI workloads at scale. While everyone's talking about model performance, the real bottleneck is happening at the infrastructure layer.
**What You'll Learn:**
• Why traditional Kubernetes setups fail with AI workloads
• How to architect platforms for GPU-intensive applications
• Real-world strategies from teams successfully running AI in production
• Practical steps to prepare your platform for the AI transformation
**Episode Breakdown:**
00:00 Cold Open: The AI production problem
02:30 Today's platform engineering news roundup
08:45 Deep Dive Act 1: AI workloads are breaking Kubernetes
18:20 Deep Dive Act 2: How successful teams handle AI infrastructure
**Today's News:**
• CNCF adds 21 new silver members focused on AI infrastructure
• Critical Grafana security vulnerabilities (CVE-2026-27876 & CVE-2026-27880)
• GitHub Actions 2026 security roadmap
• AWS launches new AI development tools
• Aurora PostgreSQL joins AWS Free Tier
Perfect for platform engineers, SREs, and infrastructure teams navigating the AI infrastructure challenge.
Podden och tillhörande omslagsbild på den här sidan tillhör
vibesre. Innehållet i podden är skapat av vibesre och inte av,
eller tillsammans med, Poddtoppen.