• Architect and operate high-availability, low-latency cloud infrastructure for real-time AI inference services. • Build and maintain CI/CD pipelines that support rapid, safe iteration across backend and ML systems. • Own production reliability: monitoring, alerting, incident response, and capacity planning. • Lead infrastructure automation using Infrastructure as Code (Terraform, Pulumi, etc.). • Partner closely with backend and ML engineers to productionize new models and services. • Harden our systems for security, compliance, and data protection. • Optimize cost, performance, and scalability as usage grows. • Establish best practices around observability, deployment strategies, and disaster recovery.