Postdoctoral Research Associate -Privacy Preserving Federated Learning Algorithms

Requisition Id 13899 

Overview: 

Oak Ridge National Laboratory is the largest US Department of Energy science and energy Laboratory, conducting basic and applied research to deliver transformative solutions to compelling problems in energy and security.

The Discrete Algorithms Group at Oak Ridge National Laboratory (ORNL) is seeking a postdoctoral researcher for a two-year position specializing in federated learning and privacy-preserving algorithms. The successful candidate will focus on advancing secure, trustworthy, and efficient AI solutions for scientific applications. Key responsibilities include developing state-of-the-art differential privacy techniques for large-scale models across multiple institutions and disseminating findings through publications and presentations in top-tier peer-reviewed journals and conferences. This role provides a unique opportunity to work with the world’s first exascale system, Frontier, and collaborate with leading experts in machine learning, optimization, electric grid analytics, and scientific imaging.

The successful candidate will design and implement differential privacy solutions for large-scale scientific data models in federated learning environments. You will advance privacy-preserving machine learning by developing efficient techniques that maintain robust privacy guarantees while minimizing performance impact. Additionally, he/she  will optimize the balance between privacy and utility, addressing the challenges of heterogeneous privacy budgets and varying requirements across diverse clients. This role offers a unique opportunity to make significant theoretical and applied contributions to differential privacy in federated learning, helping to advance secure, collaborative AI systems on a global scale.

As a U.S. Department of Energy (DOE) Office of Science national laboratory, ORNL has an extraordinary 80-year history of solving the nation’s biggest problems. We have a dedicated and creative staff of over 6,000 people! Our vision for diversity, equity, inclusion, and accessibility (DEIA) is to cultivate an environment and practices that foster diversity in ideas and in the people across the organization, as well as to ensure ORNL is recognized as a workplace of choice. These elements are critical for enabling the execution of ORNL’s broader mission to accelerate scientific discoveries and their translation into energy, environment, and security solutions for the nation.

Major Duties and Responsibilities:

• Designing novel differential privacy algorithms for large-scale AI models to advance research efforts across scientific systems.
• Developing mathematical analysis to bound the trade-off between privacy and utility especially in the context of large AI models.
• Contribute to the research and development of federated learning algorithms on distributed and heterogeneous datasets.
• Designing more efficient and resilient DP techniques over state of the art methods that minimize performance loss while still providing robust privacy guarantees.
• Designing privacy-preservation methods that accommodate the diverse privacy requirements of a large number of clients.
• Advance knowledge of key AI methods such as deep learning, algorithm design, probability theory, privacy definitions, and apply it to develop efficient privacy preserved federated learning model.

Basic Qualifications:

• A PhD in computer science, applied mathematics, computational science, or related discipline completed within the last five years.
• Demonstrated hands-on experience and understanding of developing and applying privacy preservation methods to ML models.
• Demonstrated research experience with AI and ML techniques.

Preferred Qualifications:

• Knowledge of differential privacy models such as approximate differential privacy, Local differential privacy, Rényi differential privacy, Bayesian differential privacy.
• Knowledge of distributed optimization and consensus algorithms.
• Knowledge of large models and hyper-parameter optimization.
• Knowledge of high-performance computing and its applications.

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.

Please submit research statement and transcript when applying to this position. Kindly provide the names of three references that can attest to your research expertise and record. Should the candidate be shortlisted they will be asked to arrange for letters of reference be sent directly via email to postdocrecruitment@ornl.gov and womblerl@ornl.gov  with 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

Benefits at ORNL: 

ORNL offers competitive pay and benefits programs to attract and retain talented people! The laboratory offers many employee benefits, including medical and retirement plans and flexible work hours, to help you and your family live happy and healthy. Employee amenities such as on-site fitness, banking, and cafeteria facilities are also provided for 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.

If you have difficulty using the online application system or need an accommodation to apply due to a disability, please email: ORNLRecruiting@ornl.gov

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.