Vineet Kumar Sharma

• Design, build, and operate highly available GenAI inference platforms running on
GPU-based Kubernetes clusters, supporting millions of inference requests under peak
traffic.
• Manage large-scale AWS and Azure infrastructure using Terraform, enabling
reproducible, compliant environments.
• Implement CI/CD pipelines for containerized deployments using Jenkins and GitHub.
• Lead production readiness reviews, performance tuning, and capacity planning
initiatives.
• Act as L3 on-call responder, leading major incidents, driving root-cause analysis (RCA),
and implementing long-term preventive fixes.
• Achieved 30-40% cloud cost reduction via right-sizing, autoscaling, and savings plan
optimization.
• Implement observability using Prometheus, Grafana, and enterprise monitoring tools.
• Automated operational workflows using Python and Bash, reducing manual effort and
operational errors.