PNNL is looking to solve complex scientific challenges by developing multiscale and multiphysics models, employing advanced scientific machine learning tools, and deploying these models in high-performance computing environments.
Requirements
- Computational science and/or applied mathematics background with emphasis on being able to combine physics-based computational tools with machine learning methods to model complex chemical systems.
Responsibilities
- Work on the development of hybrid machine learning force fields for applications in chemical physics problems.
- Establish new capabilities in developing physics-based computational tools able to be combined with machine learning methods to model complex chemical systems with quantitative accuracy in comparison to quantum chemistry calculations.
- Apply advanced scientific computing and machine learning methods to enhance our understanding of complex chemical systems by writing software that enables and assists in the development of hybrid physics/machine learning interaction potentials.
- Develop and optimize workflows for large-scale quantum chemistry simulations and related scientific workflows.
- Interact, communicate, and solve problems with a diverse team of applied mathematics, computational science, and experimental research staff within the ACMDD group and across PNNL.
- Publish your results in high-quality, peer-reviewed journals.
- Present your research at technical conferences and project and program review meetings.
Other
- BS/BA and 2 years of relevant experience -OR-
- MS/MA -OR-
- PhD
- Participate in the development of research proposals.
