Postdoctoral Research Associate - Sparse Algorithms

Requisition Id17201

Overview:

The Discrete Algorithms Group at Oak Ridge National Laboratory (ORNL) seeks a postdoctoral researcher for a two-year position specializing in sparse algorithms. This researcher will focus on advancing secure, trustworthy, and efficient AI solutions for scientific applications by developing state-of-the-art sparse algorithms in matrices, tensors, and networks. These algorithms will support large-scale numerical, scientific, and AI models. The researcher will also disseminate findings through publications and presentations in top-tier peer-reviewed journals and conferences. To conduct this work, the successful candidate will use the world's first exascale system, Frontier, and collaborate with leading experts in machine learning, optimization, electric grid analytics, and scientific imaging.

The primary responsibility of this position is designing and implementing sparse algorithms for large-scale scientific and numerical computations. The successful candidate will pursue an ambitious research agenda to drastically advance the state of the art in sparse computation. This research will explore sparse computations both as a unified topic and within three broad pillars: sparse and structured matrix computations, sparse tensor problems, and sparse network problems, as well as their interconnections. These efforts will yield significant theoretical and applied contributions, helping to advance sparse AI and numerical systems globally.

Major Duties/Responsibilities include, but are not limited to:

• Designing novel sparse algorithms - including mixed-precision, energy-efficient, and accelerator-optimized methods - for large-scale numerical, scientific, and/or AI models.
• Demonstrating the scalability of new algorithms on leadership supercomputers for large-scale problems of national and societal interest.
• Developing mathematical analyses to bound the trade-offs between performance, energy efficiency, and time, especially in the context of sparse computations.
• Communicating research via publications and conference presentations in top venues, invited talks, and organized workshops, tutorials, and symposiums.
• Releasing research software as open-source libraries and contributing to community codes.
• Collaborating with domain scientists to apply sparse algorithms to DOE mission applications and mentoring and working with undergraduate and graduate students.

Basic Qualifications:

• A PhD in Computer Science, Applied Mathematics, Computational Science, or a related discipline.
• Demonstrated depth in at least one of the areas of specialization listed below, evidenced by publications, software, or comparable research output.
• Demonstrated hands-on experience developing and applying HPC algorithms to sparse numerical, scientific, and ML models.

Preferred Qualification:

Strong expertise in two or more of the following areas is preferred, and an exceptionally strong candidate in a single area is also encouraged to apply. Relevant areas include:

• Parallel and distributed graph and or ML algorithms - shortest paths, connectivity, clustering, or graph traversal on GPU clusters and distributed-memory systems.
• Sparse direct and iterative linear solvers - communication-avoiding methods, sparse LU factorization, sparse triangular solves, or preconditioning.
• Mixed-precision and approximate numerical computation - floating-point error analysis, iterative refinement, or exploiting low-precision arithmetic on modern accelerators.
• Sparse and constrained tensor decompositions - CP- or Tucker-type factorizations, constrained least-squares solvers, or scalable tensor kernels.
• GPU performance engineering - CUDA/HIP kernel design, communication-computation trade-offs, or performance modeling on heterogeneous systems.
• Theory of parallel algorithms - communication lower bounds or work-depth analysis of sparse and graph computations.

Special Requirements:

Applicants cannot have received their Ph.D. more than five years prior to the date of application and must complete all degree requirements before starting their appointment. The appointment length will be up to 24 months with the potential for extension. Initial appointments and extensions are subject to performance and availability of funding.

• For employment at Oak Ridge National Laboratory (ORNL), a Real ID compliant form of identification will be required. Additionally, ORNL is subject to Department of Energy (DOE) access restrictions. All employees must also be able to obtain and maintain a federal Personal Identity Verification (PIV) card as mandated by Homeland Security Presidential Directive 12 (HSPD-12) and Department of Energy (DOE) Order 473.1A, which requires a favorable post-employment background investigation.
• To obtain this credential, new employees must successfully complete and pass a Federal Tier 1 background check investigation. This investigation includes a declaration of illegal drug activities, including use, supply, possession, or manufacture within the last year. This includes marijuana and cannabis derivatives, which are still considered illegal under federal law, regardless of state laws.
• For foreign national candidates: If you have not resided in the U.S. for three consecutive years, you are not eligible for the PIV credential and instead will need to obtain a favorable Local Site Specific Only (LSSO) risk determination to maintain employment. Once you meet the three-year residency requirement, you will be required to obtain a PIV credential to maintain employment.

Please submit three letters of reference when applying to this position. You may upload these directly to your application or have them sent toPostdocrecruitment@ornl.govwith the position title and number referenced in the subject line.

Instructions to upload documents to your candidate profile:

• Login to your account via jobs.ornl.gov
• View Profile
• Under the My Documents section, select Add a Document

About ORNL:

As a U.S. Department of Energy (DOE) Office of Science national laboratory, ORNL has an impressive 80-year legacy of addressing the nation's most pressing challenges. Our team is made up of over 7,000 dedicated and innovative individuals! Our goal is to create an environment where a variety of perspectives and backgrounds are valued, ensuring ORNL is known as a top choice for employment. These principles are essential for supporting our broader mission to drive scientific breakthroughs and translate them into solutions for energy, environmental, and security challenges facing the nation.

ORNL offers competitive pay and benefits programs to attract and retain individuals who demonstrate exceptional work behaviors. The laboratory provides a range of employee benefits, including medical and retirement plans and flexible work hours, to support the well-being of you and your family. Employee amenities such as on-site fitness, banking, and cafeteria facilities are also available for added convenience.

Other benefits include the following: Prescription Drug Plan, Dental Plan, Vision Plan, 401(k) Retirement Plan, Contributory Pension Plan, Life Insurance, Disability Benefits, Generous Vacation and Holidays, Parental Leave, Legal Insurance with Identity Theft Protection, Employee Assistance Plan, Flexible Spending Accounts, Health Savings Accounts, Wellness Programs, Educational Assistance, Relocation Assistance, and Employee Discounts.

This position will remain open for a minimum of 5 days after which it will close when a qualified candidate is identified and/or hired.

We accept Word (.doc, .docx), Adobe (unsecured .pdf), Rich Text Format (.rtf), and HTML (.htm, .html) up to 5MB in size. Resumes from third party vendors will not be accepted; these resumes will be deleted and the candidates submitted will not be considered for employment.

If you have trouble applying for a position, please email ORNLRecruiting@ornl.gov.

ORNL is an equal opportunity employer. All qualified applicants, including individuals with disabilities and protected veterans, are encouraged to apply. UT-Battelle is an E-Verify employer.