Host: Cedric Clyburn Guest: Sean Rickerd Producer: Rohan Venkatram 👉 What you’ll see in this episode: Following along - https://www.redhat.com/architect/portfolio/detail/140-confidential-containers-gtc-interactive-experience?intcmp=RHCTG0250000458743 🔐 Zero-Trust AI & Confidential Containers Why Zero Trust is now a compliance requirement Isolating AI workloads on OpenShift Running models on NVIDIA H100 Confidential GPUs 🔹 Protecting AI Models with CoCo + NIM Preventing download, copying, and redistribution Secure API key injection into trusted environments Enforcing “container-only” model access 🔹 Kubernetes Security with RHACS Build, deploy, and runtime protection Vulnerability and misconfiguration detection Runtime threat detection and policy enforcement 🔹 Zero Trust Workload Identity Identity-based service-to-service access Securing PostgreSQL without exposed credentials Enforcing least privilege and reducing lateral movement 🔹 End-to-End Secure AI on OpenShift Combining CoCo + RHACS + Workload Identity Securing the full AI lifecycle 🔹 Interactive Q&A with Cedric & Sean 🕹️ Interactive Demo / Reference: https://www.redhat.com/architect/portfolio/detail/140-confidential-containers-gtc-interactive-experience?intcmp=RHCTG0250000458743 🎯 Episode Overview: Cedric Clyburn returns with another Demo Deep Dive, joined by Sean Rickerd, Principal Technical Marketing Manager at Red Hat and a seasoned security leader with over 20 years of experience across enterprise security, DevSecOps, and cloud-native architectures. In this episode, we explore how organizations can securely deploy and scale AI workloads using Confidential Containers and Red Hat Advanced Cluster Security (RHACS) on OpenShift. As AI adoption accelerates, so do concerns around data privacy, model protection, and regulatory compliance. Sean breaks down how Zero Trust principles apply to modern AI systems—and why traditional security approaches fall short when dealing with proprietary models and sensitive data. We’ll walk through a real-world use case leveraging NVIDIA NIM containers, showing how organizations can prevent model exfiltration, enforce strict runtime controls, and ensure that even the infrastructure cannot access sensitive workloads. The session also highlights how RHACS provides full-stack Kubernetes security—from vulnerability management to runtime threat detection—alongside Workload Identity to secure service-to-service communication, including safely connecting applications to PostgreSQL without exposing credentials. Whether you're building AI platforms, securing Kubernetes environments, or navigating compliance requirements, this episode demonstrates how Red Hat enables secure, scalable, and production-ready AI deployments with a Zero Trust foundation. 🔗 Learn more and interact: 📌 Confidential Containers on OpenShift – https://www.redhat.com/en/blog/introducing-confidential-containers-bare-metal 📌 Red Hat Advanced Cluster Security (RHACS) – https://www.redhat.com/en/technologies/cloud-computing/openshift/advanced-cluster-security-kubernetes 📌 NVIDIA NIM – https://developer.nvidia.com/nim 📌 Explore OpenShift – https://www.redhat.com/en/technologies/cloud-computing/openshift 📌 Follow Cedric – https://www.cedricclyburn.com/ 📅 Livestream: Tuesday, April 7th @ 11am ET ▶️ Watch live or on-demand on @RedHat and @OpenShift #RedHat #OpenShift #KubernetesSecurity #ConfidentialContainers #ZeroTrust #AIsecurity #RHACS #DevSecOps #CloudSecurity #EnterpriseAI #HybridCloud #NVIDIA #AIInfrastructure

 272      7