Overview
What this challenge is about.
Receive 30 days of cluster metrics (Prometheus + AWS Cost Explorer exports), Helm releases, and PodDisruptionBudgets per namespace. Profile: identify the top 3 cost drivers (likely candidates: oversized requests, mono-instance-type node groups, missing Spot adoption, unscheduled-replica bloat). Prototype: (1) right-size requests via VPA recommendations across the top 20 namespaces, (2) introduce a Spot-heavy node group with PDB-aware scheduling, (3) switch one stateless workload to Karpenter-managed nodes. Run a 7-day pilot on the prototype on a representative 40-node carve-out. Deliver profiling report, prototype Helm + Terraform, 7-day pilot results, and a 6-page rollout plan to take the full cluster from USD 240k/month to under USD 156k/month.
The Brief
What you'll do, and what you'll demonstrate.
Cut a 280-node EKS cluster's monthly cost by 35 percent without violating customer SLAs, proving the saving on a 40-node pilot first.
Earning criteria — what you'll demonstrate
- Profile Kubernetes cluster cost across nodes, requests, and idle capacity
- Apply right-sizing using Vertical Pod Autoscaler recommendations
- Introduce Spot + Karpenter without breaking PDBs or SLAs
- Plan a cluster-wide rollout staged for safe reversal
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Career mappings coming soon.