Senior Research Computing Storage Engineer

Details

Posted : 29-Jul-24

Location : Cambridge, Massachusetts

Type : Full Time

Salary : $115,000 - $125,000

Categories :

Technical (Programmer, Developer, Analyst)

Internal Number : 66073BR

Reporting to the Associate Director of Storage Services and collaborating closely with the storage group, this role is pivotal in the design, implementation, and upkeep of crucial storage services.

As a senior member of the team, you will play a key role in understanding both present and future storage requirements for FAS Research Computing (RC) users.

Your responsibilities will encompass grasping the intricacies of storage technology and collaborating with the team to deliver robust storage solutions at a production level.

The role necessitates the ability to handle various projects concurrently, offer guidance and training to junior team members as needed, and extend knowledge and support to the department.

Familiarity with the operations of a datacenter environment is essential, given Harvard FAS RC's management of on-premises services.

Research Computing at Harvard is an enterprise that continues to reflect the University’s decentralized heritage, the evolution of research-computing infrastructure and funding opportunities, and the strategic development of its central information-technology organization, Harvard University Information Technology (HUIT) and its University Research Computing team.

Faculty of Arts & Sciences Research Computing

Starting in 2007, FAS began consolidating and centralizing research-computing resources within the Division of Sciences and soon began expanding across the School as faculty in the social sciences and humanities began to use advanced computing in their research.

The organization came to be called and, as more and more faculty across Harvard came to it for support, it extended its services beyond FAS, increasingly in collaboration with HUIT.

With HUIT now developing an array of University-wide services and platforms to support faculty beyond FAS, FAS has the opportunity to strategically redefine what resources and services it will continue to support for the Arts & Sciences at Harvard and to broaden the base of users across the School who are advancing their research through computing.

In this context, FAS Research Computing continues to evolve, to expand its offerings, and to support research faculty across the School and their collaborators around the world.

It has earned a reputation for building partnerships to accelerate research and collaboration. The Director of FAS RC will continue this legacy.

FAS’ research computing team directly engages with researchers through help requests, office hours, training, and in-depth consultations.

FAS resources include a high- performance computing cluster, virtual machines, storage, databases, instrumentation core facility workstations, and other development platforms.

FAS Research Computing has numerous other successful collaborations, including building the MGHPCC in Holyoke, MA with leading partner universities.

With these and other institutions, FAS launched the NSF-funded NESE project (), which creates a regional cloud storage repository.

Basic Qualifications :

Minimum of seven years’ post-secondary education or relevant work experience

Additional Qualifications :

• Broad knowledge in the deployment and management of systems encompassing storage, cluster computing, network, and databases.
• Advanced proficiency in Linux system administration is preferred.
• Understanding and preferably experience with OSI model, Layer 2 & 3 switching and routing, TCP / IP.
• Evaluating, deployment, and managing of open-source tools such as EC2, EBS, and S3.
• Familiarity with Storage Area Networks (SAN) and Network Attached Storage (NAS), including protocols like iSCSI, NFS, and FC.
• Experience with one or more parallel file systems such as EMC / Isilon, VAST, Lustre, GPFS, Gluster, or Ceph.
• Familiarity with data management and Hierarchical Storage Management (HSM) tools like Starfish, Ngenea, and Robinhood is advantageous.
• Proficient in performance tuning and troubleshooting of complex systems, including application load balancing solutions for scaling and High Availability (HA).
• Occasional visits to data centers for vendor liaison, installations, maintenance / repair, etc.

About Harvard University