Overview
What this challenge is about.
Receive 30 days of anonymized placement requests (workload CPU/memory shape, affinity rules), zone capacity per day, and cross-zone bandwidth costs. Model the placement as a min-cost max-flow: source → workloads → eligible zones (with affinity edges) → sink, where edge costs encode bandwidth + balance, and capacities encode zone limits. Implement using SSP (Successive Shortest Path) or capacity scaling; do not call a black-box solver. Benchmark on 30 days vs. the greedy baseline on cost per workload and zone-balance variance. Deliver code, formulation memo, and 6-page architecture rationale.
The Brief
What you'll do, and what you'll demonstrate.
Replace a greedy workload placer with a min-cost max-flow formulation that respects affinity rules and beats the baseline on bandwidth cost and zone balance.
Earning criteria — what you'll demonstrate
- Model a real placement problem as min-cost max-flow with affinity edges
- Implement a polynomial-time min-cost flow algorithm without a solver
- Benchmark a flow-based solution against a greedy heuristic at scale
- Defend network-flow modeling choices to senior engineering leadership
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.