• Platform Support & Incident Response
• Provide Tier 1 & Tier 2 support for AI-driven platforms and workloads.
• Troubleshoot and resolve issues related to AI Gateway, model hosting, Kubernetes deployments, GPU utilization, and service performance.
• Collaborate with Tier 3+ teams, including network, storage, and Kubernetes engineers as well as vendors, to escalate and resolve complex issues.
• Kubernetes & Cloud-Native Operations
• Full adoption, creation, and integration into automated services using Jenkins, Helm, Ansible, Terraform, etc.
• Deploy, manage, and support containerized AI workloads on on-prem Google Anthos-powered Kubernetes clusters, AWS, and GCP.
• Ensure adherence to pod security policies, automated rollouts/rollbacks, and best practices for scalable and secure Kubernetes environments.
• GPU Infrastructure & AI Services Management
• Optimize and support GPU-enabled workloads including CUDA and other AI acceleration frameworks.
• Assist in the installation, configuration, and support of AI coding assistants (e.g., Codeium).
• Observability & Documentation
• Maintain detailed operational documentation, runbooks, and troubleshooting guides.
• Utilize monitoring/logging tools like New Relic, Prometheus, Grafana, and other observability frameworks.
• Process Improvement & Collaboration
• Work cross-functionally with developers, IT teams, and vendors to ensure seamless deployment and support of AI services.
• Contribute to CI/CD pipelines, automation, service, and security best practices.
• Track and communicate work through task management platforms (ServiceNow and Jira).
