Postdoc: AI/ML for Uncertainty Quantification in Materials

Sandia National Laboratories; Livermore (CA); On-site; USD 90,000 - 120,000; Full time

Job summary

Sandia National Laboratories seeks a highly motivated Postdoctoral Appointee to join a multidisciplinary team at the intersection of computational science and data-driven modeling. The role includes AI/ML methods for uncertainty quantification in multiscale materials and hybrid modeling that couples full-order and reduced-order models.

The candidate will work with Sandia PIs, national labs, and universities, applying adaptive hybrid modeling to solid mechanics with a focus on online switching

Qualifications

• PhD in a field of physical sciences, applied mathematics, engineering, or other relevant field conferred within five years prior to employment.
• Knowledge and expertise in machine learning and/or uncertainty quantification.
• Knowledge and expertise in projection-based reduced order modeling and/or operator inference.
• Knowledge and expertise in computational science and/or software development.
• This position requires access to export-controlled or ITAR information. Only U.S. persons (citizens, lawful permanent residents, asylees or refugees) are eligible for consideration.

Responsibilities

• Develop AI/ML methods for uncertainty quantification in multiscale materials modeling and data-driven modeling efforts.
• Develop domain decomposition-based hybrid modeling approaches that couple full-order, reduced-order, and data-driven models.
• Collaborate with Sandia Principal Investigators and scientists from other national laboratories and universities.
• Work onsite and contribute to adaptive hybrid modeling for solid mechanics exemplars.

Skills

Machine learning

Uncertainty quantification

Reduced order modeling

Computational science

Software development

C++

Python

Julia

Collaborative research

Communication skills

Education

PhD in physical sciences / applied mathematics / engineering

Tools

PyTorch

JAX

Julia

C++

Python

Job description

Sandia National Laboratories seeks a highly motivated Postdoctoral Appointee to join a multidisciplinary team at the intersection of computational science and data-driven modeling. The role includes AI/ML methods for uncertainty quantification in multiscale materials and hybrid modeling that couples full-order and reduced-order models.

The candidate will work with Sandia PIs, national labs, and universities, applying adaptive hybrid modeling to solid mechanics with a focus on online switching