Design, build, and operate AWS and Kubernetes infrastructure powering production AI systems. Own CI/CD, infrastructure as code, GitOps, observability, secrets management, GPU workloads, model serving, reliability, security, scalability, and cost optimization. Troubleshoot production incidents, perform root-cause analysis, and develop automation using Python and Bash while collaborating across Engineering, ML/AI, Security, and Product teams.

Lead technical support for B2B customer deployments, diagnosing issues across ML models, applications, APIs, infrastructure, networking, and deployment environments. Investigate incidents, review logs and configurations, coordinate escalations with FDE, SRE, and Engineering teams, monitor deployment health, document root causes, communicate with customer stakeholders, and develop tools and dashboards to meet support SLOs.