Storage Architect

Jefferson Lab; Newport News (VA); On-site; USD 118,000 - 187,000; Full time

Benefits offered by this job

Medical, Dental, and Vision Plans

401(k) Plan – Lab contribution

Flexible Work Arrangements

Job summary

Jefferson Lab seeks a Lead Storage Architect to design and own the High-Performance Data Facility (HPDF) storage. You’ll shape multi-tier, distributed storage across sites and drive performance, cost models and architecture choices.

You will research and compare commercial and open-source storage solutions, define SLOs/SLIs, and lead the storage operations team after deployment. DOE-aligned mission and large-scale data workflows.

Qualifications

• Experience with hybrid cloud architectures for HPC workloads.
• Experience designing multi-tiered, highly available storage architectures across distributed locations.
• 10+ years in HPC, scientific computing, or large-scale distributed systems.
• 4+ years deploying petabyte-scale parallel/distributed file systems.

Responsibilities

• Lead the technical design of a multi-tiered, widely distributed storage system with high throughput and data integrity.
• Evaluate storage tech (HPC platforms, open-source file systems, cloud) and support acquisition decisions.
• Develop performance and TCO models; define benchmarking strategies.
• Define SLOs/SLIs and implement monitoring for design validation and operations.
• Define operating framework and staffing plans for the storage team.

Skills

HPC storage

Distributed systems

Storage performance modeling

Cost modeling

Vendor evaluation

Education

Bachelor's Degree Computer Science/Information Systems

Master's Degree preferred

Tools

VAST

Weka

IBM Spectrum Scale

Lustre

Ceph

DAOS

Job description

At Jefferson Lab, you’ll champion cutting-edge science and operational excellence while shaping the future of discovery. Join us and make your mark – where excellence meets purpose, and great mindstruly matter.

The good-faith pay range for this role is $118,400 - $186,500 per year. Actual compensation may vary and may be above the posted range based on factors such as a candidate's skills, experience, education, certifications, and work location.

What Your Job Will Be Like

Jefferson Lab, in collaboration with Lawrence Berkeley National Laboratory are building the High-Performance Data Facility (HPDF), a landmark DOE ASCR investment in scientific data infrastructure. Spanning from the Virginia coast to the California Bay Area, HPDF will deliver seamless, integrated data services across both institutions, purpose-built for the demands of modern data science and research. Unlike traditional facilities where data is an afterthought, HPDF is designed to be a data-first facility that will treat scientific data as a first-class asset and provides the capabilities researchers need to extract its full scientific value. This is a greenfield storage architecture role.

You are the principal authority on storage architecture for the High-Performance Data Facility (HPDF), leading the design of a large-scale, multi-tiered, distributed storage system purpose-built for DOE scientific data lifecycle. You research and evaluate the full landscape of commercial vendors, cloud providers, and open-source distributed storage solutions, develop performance and cost models, and work closely with peer architects to ensure coherent, well-grounded technology selections as the project advances toward its design milestones. When the facility is complete, you lead the HPDF storage operations team, owning storage infrastructure across its distributed locations.

In This Job You Will

• Design Leadership: Lead the technical design of a multi-tiered, widely distributed storage system incorporating reliability, immutability, data integrity, and high-throughput performance across distributed locations.
• Evaluate storage technologies: HPC platforms (VAST, Weka, Spectrum Scale), open-source file systems (Lustre, DAOS, Ceph), and cloud. Engage vendors, assess solutions, and develop analyses to support architecture and acquisition decisions.
• Performance and Cost Modeling: Develop and validate models to predict storage performance, capacity, and total cost of ownership at scale. Define KPPs and benchmarking strategies to govern storage system selection and validation.
• Metrics and Observability: Define initial SLOs and SLIs for storage performance and availability. Architect and implement monitoring and alerting solutions supporting design validation and future facility operations.
• Establish Storage Team Framework: Define the operational framework and staffing plans for the future storage team, which will be responsible for the lifecycle management of the entire storage infrastructure.

Lead - Supervisory - Management

• Lead small team

Experience

• Required: Experience with hybrid cloud architectures for HPC workloads including cloud bursting and cross-site data movement over a WAN.
• Preferred: Experience at a DOE national laboratory, research university HPC center, or equivalent scientific computing environment.
• Required: 10 or more years HPC, scientific computing, large-scale distributed systems, or equivalent.
• Required: 4 or more years designing and deploying high-performance parallel or distributed file systems at petabyte scale or beyond.
• Required: Experience designing multi-tiered, highly available, and resilient storage architectures, including data staging, archival, and immutability strategies across distributed locations.
• Required: Hands-on experience designing and deploying parallel or distributed file systems at petabyte scale or beyond in an HPC or scientific computing environment.
• Required: Experience developing storage performance models, capacity planning frameworks, and total cost of ownership analyses at facility scale.

Education

• Required: Bachelor's Degree Computer Science, Information Systems, or other relevant information technology
• Preferred: Master's Degree Computer Science, Information Systems, or other relevant information technology

Experience And Education Exchange

Education above the minimum may be substituted for experience. Relevant experience may not be substituted for education.

Knowledge, Skills, And Abilities

• Deep expertise in HPC storage technologies including parallel file systems, distributed file systems, object storage, cloud storage, tape libraries, SAN, and NAS.
• Deep understanding of storage networking protocols and interconnects including Fibre Channel, iSCSI, NVMe-oF, and high-speed data transfer technologies relevant to high-throughput data workflows.
• Evaluating and deploying commercial high-performance storage solutions (e.g. VAST, Weka, IBM Spectrum Scale) and open-source distributed file systems (e.g. Ceph, Lustre, DAOS) against performance, reliability, and cost requirements.
• Familiarity with scientific data workflows including detector data ingest, MPI-IO access patterns, and HSM. (Preffered)
• Familiarity with data integrity, encryption, and compliance requirements including FAIR data principles, data retention policies, and relevant federal data management standards. (Preffered)

About Jefferson Lab

Join a community with a common purpose of solving the most challenging scientific and engineering problems of our time. The Jefferson Lab campus is located in southeastern Virginia amidst a vibrant and growing technology community.

A career at Jefferson Lab is more than a job. You will be part of “big science” and work alongside top scientists and engineers from around the world unlocking the secrets of our visible universe. Managed by SURATech, LLC, Thomas Jefferson National Accelerator Facility is entering an exciting period of mission growth and is seeking new team members ready to apply their skills and passion to have an impact. You could call it work, or you could call it a mission. We call it a challenge. We do things that will change the world.

Total Rewards at Jefferson Lab

Benefits

At Jefferson Lab, we believe that a comprehensive employee benefits program is an important and meaningful part of the compensation employees receive. Our benefits program includes, but is not limited to:

• Medical, Dental, and Vision Care Plans
• Flexible Spending Accounts
• Paid Time-off and Leave Programs (Paid Parental, vacation, holidays, and sick leave)
• 401(k) Plan – 9% Lab Contribution; 100% vested
• Flexible Work Arrangements

(Remote & Alternate Work Schedules available)

• Tuition Assistance, Training and Professional Development Programs
• Live near the waterways of the Chesapeake Bay region with access to nearby beaches, mountains, and all major metropolitan centers on the East Coast

SURATech, LLC manages and operates the Thomas Jefferson National Accelerator Facility (Jefferson Lab). SURATech is an Equal Opportunity Employer.

SURATech is committed to providing reasonable accommodation for people with disabilities (unless doing so will result in an undue hardship). If you need a reasonable accommodation for any part of the employment process, please send an e‑mail to [e-mail] or contact Human Resources by calling [phone] and selecting option 1 between 8 am – 5 pm EST to provide the nature of your request.

Employment with SURATech is conditional upon DOE approval if at any time during your employment you are participating in a Foreign Government Talent Recruitment Program or Affiliated activity. Generally, such programs/activities include any foreign-state-sponsored attempt to acquire U.S.-funded scientific research through programs run or funded by the government that target scientists, engineers, students, academics, researchers, and entrepreneurs of all nationalities working or educated in the United States. This includes positions or appointments, both domestic and foreign, titled academic, professional, or institutional appointments whether or not remuneration is received and whether full-time, part-time or voluntary.