Ceph Engineer / Developer
On-siteToronto, Ontario, Canada or Montréal, Quebec, Canada
Job Summary
Deep-dive into Ceph code and architecture (RADOS, RGW, core storage) to optimize performance and scalability for production workloads spanning tens of petabytes. Profile, benchmark, and troubleshoot performance issues at scale to identify architectural bottlenecks, while developing internal build pipelines and extensions ensuring long-term maintainability. Lead knowledge development and mentorship on Ceph expertise across IaaS and Operations teams, and actively contribute upstream to the Ceph project by submitting patches and influencing critical features. Partner with Platform Operations to enhance observability and accelerate issue resolution in production clusters, collaborating with squads to evolve capabilities for upcoming roadmap items like GPU-aaS and Backup-aaS.
Required Qualifications
- Proven track record operating Ceph at scale (multi-petabyte, high-availability clusters) in production environments.
- Strong C++ development experience for system-level software, especially within Ceph core components.
- In-depth knowledge of performance tuning (OSD placement, CRUSH maps, BlueStore tuning, cache tiering, RGW optimization).
- Solid understanding of Linux systems engineering, networking, and storage I/O paths.
- Proficiency with Ansible (playbooks, roles, collections) for large-scale operations and Python for custom modules, Ceph tooling, and automation workflows.
- Hands-on experience with performance analysis tools (perf, flamegraphs, distributed tracing).
- Bachelor's degree in Engineering, Computer Science, or a related field, or equivalent experience and training.
- Valid work permit in Canada
Desired Qualifications
- Familiarity with Go for building lightweight or performance-sensitive utilities is an asset.
- Prior contributions to Ceph or other distributed storage projects (patches, reviews, or design documents).
- Knowledge of cloud platforms such as OpenStack and their storage integrations.
- Relevant technical certifications are an asset.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.