Postdoc: AI/ML for Uncertainty in Multiscale Materials

Sacbar; Livermore (CA); On-site; USD 70,000 - 100,000; Full time

Benefits offered by this job

Flexible work arrangements

Relocation assistance

Comprehensive medical benefits

Generous vacation and retirement plan

Job summary

Sandia National Laboratories seeks a highly motivated Postdoctoral Appointee to work at the intersection of computational science, applied math, and data-driven modeling. You will contribute to AI/ML methods for uncertainty quantification in multiscale materials modeling and to domain decomposition-based hybrid modeling that couples full-order and reduced-order models.

The role involves developing adaptive methods for online switching between ROMs and FOMs, balancing efficiency and accuracy, and

Qualifications

• PhD required or conferred within five years prior to employment.
• Strong background in ML and/or uncertainty quantification.
• Experience with projection-based ROM and/or operator inference.

Responsibilities

• Conduct research on AI/ML methods for uncertainty quantification in multiscale materials modeling.
• Develop domain decomposition-based hybrid modeling approaches and adapt online ROM/FOM switching.
• Collaborate with principal investigators and researchers across national laboratories and universities.

Skills

Machine learning

Uncertainty quantification

Reduced order modeling

Software development

Python

C++

Julia

Team collaboration

Communication skills

Education

PhD in physical sciences / applied mathematics / engineering

Tools

PyTorch

JAX

Job description

Sandia National Laboratories seeks a highly motivated Postdoctoral Appointee to work at the intersection of computational science, applied math, and data-driven modeling. You will contribute to AI/ML methods for uncertainty quantification in multiscale materials modeling and to domain decomposition-based hybrid modeling that couples full-order and reduced-order models.

The role involves developing adaptive methods for online switching between ROMs and FOMs, balancing efficiency and accuracy, and