Principal Ceph Engineer

📋 Description

• • Own the end-to-end lifecycle of GoDaddy’s multi-petabyte Ceph storage clusters that power millions of customer websites, email accounts, and managed databases across 20+ global data centers. You will architect, scale, and harden the storage fabric that underpins our public cloud, VPS, and shared-hosting products.
• • Serve as the technical authority for Ceph at GoDaddy, translating business growth forecasts into storage capacity plans, performance models, and cost-optimization roadmaps. Your designs will directly influence how fast we can onboard new customers and how reliably we can serve them.
• • Lead root-cause analysis for the most complex storage incidents—think OSD flapping, slow bluefs transactions, or PG imbalance under massive rebuild storms—and turn lessons learned into automated safeguards, runbooks, and upstream contributions that benefit the entire Ceph community.
• • Drive zero-downtime upgrades of Ceph releases (currently Pacific → Quincy → Reef) across heterogeneous hardware generations (NVMe, SATA, SMR, and QLC tiers) while maintaining sub-millisecond tail latency for our highest-value e-commerce and WordPress workloads.
• • Build and mentor a distributed team of senior storage engineers, SREs, and kernel hackers. You will conduct architecture reviews, pair-program on critical PRs, and champion a culture of blameless post-mortems and continuous learning.
• • Automate every repeatable task—deployments, OSD replacement, CRUSH map tuning, RGW bucket resharding—using Ansible, Salt, and internal Python tooling. Your code will be peer-reviewed, unit-tested, and continuously deployed via GitHub Actions and ArgoCD.
• • Partner with product, finance, and supply-chain teams to negotiate vendor roadmaps, forecast flash and spindle demand 12–18 months ahead, and lock in volume pricing that saves GoDaddy seven-figure annual costs without sacrificing durability or performance.
• • Instrument Ceph with Prometheus, Loki, and custom eBPF exporters to surface golden signals (latency, traffic, errors, saturation) in Grafana dashboards that executives and on-call engineers trust equally. You will define SLOs and error budgets that align engineering velocity with customer happiness.
• • Contribute upstream patches to Ceph, the Linux kernel, and related projects (BlueStore, RGW multisite, Crimson) so that GoDaddy’s innovations flow back to the open-source ecosystem and reduce our long-term maintenance burden.
• • Champion security and compliance initiatives—encryption at rest, key rotation, FIPS 140-2, SOC 2 evidence collection—ensuring that our storage layer meets or exceeds regulatory requirements for financial and healthcare verticals.
• • Present at internal tech talks, external conferences (Cephalocon, SREcon, LSF/MM), and customer webinars to showcase GoDaddy’s storage engineering excellence and attract top-tier talent to the team.
• • Influence the strategic direction of GoDaddy’s infrastructure stack, evaluating emerging technologies (CXL, computational storage, erasure-coded object tiers on S3) and running proof-of-concepts that could reshape our multi-year architecture.