Sheshank Dudaboina
SRE - AI Infrastructure
I've spent 8+ years making distributed systems more reliable, from Linux fleets to multi-cloud Kubernetes and model-serving platforms. I care about observability, reducing on-call toil, and keeping high-throughput systems boring in production.
01.Experience
Building reliability for AI model serving infrastructure across Kubernetes, GPU fleets, multi-cloud platforms, and the observability systems that keep high-throughput inference workloads healthy.
Built and operated production reliability systems for AI and customer-facing platforms. Improved Kubernetes operations, observability coverage, incident response, and automation for engineering teams.
Operated large-scale infrastructure and production services, modernized Linux and container workflows, built CI/CD pipelines, and improved on-call practices for reliability-critical systems.
Supported reliability for production services, improved operational workflows, and contributed to monitoring, automation, and incident response practices for customer-facing systems.
02.Skills
- ›AWS (EC2, EKS, RDS, S3, IAM, VPC)
- ›GCP (GKE, Cloud Run, BigQuery)
- ›Terraform
- ›Pulumi
- ›Ansible
- ›Kubernetes (EKS, GKE, self-managed)
- ›Helm
- ›ArgoCD
- ›Docker
- ›Kustomize
- ›Grafana
- ›Victoria Metrics
- ›Prometheus
- ›Loki
- ›Grafana Alloy
- ›Tempo
- ›Datadog
- ›New Relic
- ›incident.io
- ›PagerDuty
- ›SLO/SLI/Error budgets
- ›Post-mortem facilitation
- ›Go
- ›Python
- ›Bash
- ›TypeScript
- ›SQL
- ›PromQL/MetricsQL
- ›LogQL
03.Certifications
I write about what I learn on the job.
SRE / Kubernetes / GPU platforms / Observability
Read my writing →