Postdoc: Predictive Modeling for Materials Informatics

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

Benefits offered by this job

Flexible work arrangements

Relocation assistance

Generous vacation

401k benefits

Job summary

Sandia National Laboratories invites applications for a Postdoctoral Appointee in Computational Materials Chemistry, Materials Informatics, and Predictive Modeling. The role centers on developing data-driven and computational tools to understand materials behavior under extreme conditions and to accelerate discovery across multiple materials systems.

You will build and apply machine-learning models, work with experimental teams, and contribute to design of next-step experiments using

Qualifications

• PhD in a relevant STEM field with strong research background.
• Experience building, evaluating and applying ML models to experimental/computational datasets.
• Familiarity with ML for structure–property relationships in materials.

Responsibilities

• Develop and apply computational, statistical, and machine-learning approaches to analyze heterogeneous datasets to relate structure, properties and performance in materials.
• Build predictive and interpretable models linking chemistry, morphology, processing history and environment to outcomes.
• Collaborate with experimental scientists to integrate modeling with characterization data and guide interpretation of results.
• Design next-step experiments or screening strategies using uncertainty-aware modeling and active learning.

Skills

Machine learning

Data analysis

Python

Statistics

Uncertainty quantification

Active learning

Education

PhD in materials science and engineering, chemistry, chemical engineering, physics, applied mathematics, computer science, data science

Job description

Sandia National Laboratories invites applications for a Postdoctoral Appointee in Computational Materials Chemistry, Materials Informatics, and Predictive Modeling. The role centers on developing data-driven and computational tools to understand materials behavior under extreme conditions and to accelerate discovery across multiple materials systems.

You will build and apply machine-learning models, work with experimental teams, and contribute to design of next-step experiments using