Principal Software Engineer for CephFS - Distributed Storage System

Introduction
IBM’s Ceph[1] engineering organization is looking for a senior software engineer to join the CephFS team. In this role you will collaborate with our worldwide Ceph engineering team to develop and enhance CephFS[2] the file system component of the Ceph software-defined distributed storage system. You will design and implement new capabilities and features to enable new use cases while improving scalability performance and efficiency. You will participate in a vibrant and active open source community[3] to deliver enterprise-quality software.

CephFS comprises a wide-ranging software suite including Linux kernel and userspace clients a clustered userspace metadata server and a messaging layer for storing data with Ceph’s native object store (“RADOS”) in addition to higher-level APIs for integrating with other systems (OpenStack OpenShift an NFS-Ganesha cluster Samba etc). As a member of the CephFS engineering team you will have the opportunity to learn and work in many of these areas according to your experience and technical background. This role is specifically focused on experienced developers who are ready to work on new distributed algorithms to build out end-user features of the filesystem such as instant cloning file overlays and coherent snapshots across multiple clients with a coherent distributed cache.

You will work remotely with a worldwide team so communication is key. You will collaborate with others using modern open source tools including git (and GitHub) Jenkins Redmine and community-developed testing and validation tools.
[1]: https://ceph.io/en/news/publications/ https://www.youtube.com/c/Cephstorage
[2: ]https://docs.ceph.com/en/quincy/cephfs/ https://youtu.be/cNAxNSzZqzo?t=1311
[3]:https://github.com/ceph/ceph https://tracker.ceph.com/projects/cephfs

Your Role and Responsibilities
Roles and Responsibilities of a Senior Software Engineer in IBM’s Ceph Engineering Organization:

• Work closely with the global Ceph open-source multi-company engineering team to develop and enhance CephFS the file system component of the Ceph software-defined distributed storage system. You will collaborate with other developers and users by attending online meetings participating in email lists and online chat rooms preparing written documentation and giving presentations about your work. You will be expected to work proactively with other team members and the community to develop your knowledge and to be ready to mentor new contributors as you develop expertise.
• Contribute to the development of CephFS by designing and implementing new functionalities that enable innovative use cases. This includes designing new distributed algorithms implementing them across clients and servers and writing automated test cases to demonstrate they work. You will also identify and fix bugs and propose performance enhancements. This will involve work across our C++-language Metadata Server cluster and userspace clients our Linux in-kernel client (which you may either develop on your own or arrange with our kernel maintainers) and our messaging layer for storing data within Ceph’s “RADOS” distributed object store.

Required Technical and Professional Expertise
* 5-7 years of Experience working with C++ codebases or other systems languages which includes:
* Live systems (via logging and interrogation) and examining core files Good debugging skills
* Open sources Git
* Basic knowledge of Python to use and enhance testing
* Demonstrated ability to understand large codebases and develop new features
* Excellent English written and verbal communication skills for our worldwide team

Preferred Technical and Professional Expertise
* Experience with data storage and/or file systems
* Experience building distributed systems
* Experience working on distributed teams is a plus
* Past contribution to open source projects is favorable