Postdoctoral Research Associate – Machine Learning for Complex System Prognostics
Date: Oct 8, 2020
Location: Oak Ridge, TN, US, 37830
Company: Oak Ridge National Laboratory
Requisition Id 4156
The Neutron Sciences Directorate (NScD) at Oak Ridge National Laboratory (ORNL) operates the High Flux Isotope Reactor (HFIR), the United States’ highest flux reactor based neutron source, and the Spallation Neutron Source (SNS), the world’s most intense pulsed accelerator based neutron source. Together these facilities operate 30 instruments for neutron scattering research, each year carrying out in excess of 1,000 experiments in the physical, chemical, materials, biological and medical sciences. HFIR also provides unique facilities for isotope production and neutron irradiation. To learn more about Neutron Sciences at ORNL go to: http://neutrons.ornl.gov. Oak Ridge National Laboratory is also a leader in computational and computer science, with unique strengths in high-performance computing and data analytics with applications to the physical and biological sciences.
We are seeking a postdoctoral research associate who will focus on signal processing, statistical analysis, probabilistic theory and machine learning with emphasis on diagnostics and prognostics applications. This position resides in the Accelerator Science and Technology Section in the Research Accelerator Division, Neutron Sciences Diretorate at Oak Ridge National Laboratory (ORNL).
As part of our research team, you will work with accelerator and target systems specialists and machine learning experts to develop, integrate and apply machine learning methods to improve performance of the SNS 1.4 MW accelerator and target systems.
- Develop, implement and apply new machine-learning (ML) and statistical methods techniques to sensor and component health monitoring, anomaly detection and fault isolation
- Develop and apply both first-principles-based and data-driven techniques to solving complex engineering problems
- Perform uncertainty quantification and uncertainty propagation analyses
- PhD in nuclear, electrical engineering, mechanical, computer engineering, or engineering physics, computational science or a related field within the past 5 years.
- Experience with open-source machine-learning tools, such as TensorFlow, pyTorch or Keras
- Experience with applying and deploying recent machine-learning methods for solving complex engineering problems, including diagnostics and prognostics of complex engineered systems
- Experience in physics-informed machine learning for analysis of physical systems
- Experience with uncertainty quantification methods and application of those methods in complex systems
- Experience working in Linux environments on large high-performance cluster computing architectures
- Demonstrated experience in statistical methods and machine-learning methods, with a specific application to time-series datasets from multiple sensors
- Strong understanding of underlying mathematics of signal processing, filtering and machine learning to unfold unique signatures in typical noisy time-series data
- Demonstrated results-oriented problem-solving skills, and a willingness to apply those skills to a variety of engineering problems
- Excellent communication skills (verbal, presentation and scientific writing) that enable effective interaction with technical peers, program managers, and sponsors
- Strong scholarly and publication record that demonstrates independence and initiative taking
- Ability to work independently and in a team environment, thoroughly document work performed
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.
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.Apply now