Computational Scientist, Earth System Predictability

---

Job description

Requisition Id5418

Overview: The Computational Science and Engineering Division (CSED) at Oak Ridge National Laboratory (ORNL) is seeking a qualified computational research scientist in the field of Earth system science. CSED focuses on transdisciplinary computational science and analytics at scale to enable scientific discovery across the physical sciences, engineered systems, and biomedicine and health. It provides foundations and advances in quantum information sciences to enable quantum computers, devices, and networked systems. It develops community applications, data assets, and technologies and provides assurance to build knowledge and impact in novel, crosscut-science outcomes.

The Advanced computing methods for Physical Sciences Section within CSED is focused on delivering multiscale, multi-fidelity computational models and systems using algorithms and analytics for the physical sciences. Within this section, the Computational Earth Sciences group conducts world-class research and development in Earth system modeling and model development, model-data integration, large scale data analytics and machine learning, and model benchmarking at the US Department of Energy's (DOE's) Leadership Class Computing Facilities (LCFs).

Purpose

The computational scientist will focus on developing and applying models and artificial intelligence/machine learning methods to quantitatively assess, understand, and improve process predictions.

Major Duties/Responsibilities:

Research

• Collaboration within a multi-disciplinary research environment consisting of computational scientists, computer scientists, applied mathematicians, experimentalists, and engineers/physicists conducting basic and applied research in support of the Laboratory's missions.
• Conduct regional and global Earth system model (ESM) simulations.
• Develop and apply artificial intelligence and machine learning methods to construct data sets for model initialization and validation.
• Develop and implement software modules for hybrid machine learning-/process based-models of Earth system processes on high performance computing systems, and diagnose and benchmark model performance.
• Collaborate with a diverse team of Earth system and computational scientists, both within CESG and across DOE Labs and partner universities.
• Work with the research community to design and develop data mining and machine learning methods to synthesize benchmark datasets for model evaluation and data assimilation and to develop neural network approaches for representation of Earth system processes and for surrogate modeling.
• Explore Earth system feedbacks associated with physical, chemical, and biological processes.
• Publish research in peer-reviewed journals and present results at national and international conferences.
• Mentor early career research staff, postdocs and students.

Service

• Advance the reputation of the organization through establishing collaborations, professional society leadership and involvement, and organization of technical events.

Basic Qualifications:

• Requires a Ph.D. in Earth science, computer science, applied math, artificial intelligence, or a related field with a minimum of 6 years of relevant experience, a M.S. with a minimum of 12 years of relevant experience, or a B.S. with 15 years of relevant experience.
• Demonstrated experience in the design and implementation of numerical algorithms in one or more high-level computing languages (e.g. C++, Fortran, Python) to improve Earth system model development, analysis, and performance.

Preferred Qualifications:

• Experience with software engineering, high performance computing, applied mathematics, advanced statistical and machine learning methods, deep neural networks, and visual data analytics approaches
• Experience in uncertainty quantification, model and data analytics, and design and development of model evaluation methods
• Previous research experience developing and applying regional and global Earth system models
• Familiarity with data file formats and conventions (e.g., CF, netCDF, HDF)
• Experience with data manipulation and analysis packages (e.g., Ferret, IDL, Matlab, NCL, Python, R, NCO)
• Familiarity with machine learning toolkits and methods (e.g., Scikit-learn, TensorFlow, PyTorch, Keras, Caffe)
• Experience with the Linux operating system, LaTeX, Git, Python, and Fortran and/or C/C++
• Collaborative research capabilities as demonstrated by existing peer-reviewed publications and technical proposals
• Strong motivation to perform novel world-class research and publish results
• Excellent verbal and written communication skills

Relocation:Moving can be overwhelming and expensive. UT-Battelle offers a generous relocation package to ease the transition process. Domestic and international relocation assistance is available for certain positions. If invited to interview, be sure to ask your Recruiter (Talent Acquisition Partner) for details.

For more information about our benefits, working here, and living here, visit the "About" tab atjobs.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 .

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.

Nearest Major Market: Knoxville