Physics-Informed ML Postdoc: Computational Mechanics

Lawrence Livermore National Laboratory; Livermore (CA); Hybrid; USD 111,000 - 135,000; Full time

Benefits offered by this job

Flexible schedules

Job summary

Lawrence Livermore National Laboratory is seeking a Physics-Informed Machine Learning Postdoctoral Researcher to develop and apply advanced computational methods for modeling complex physical systems.

You will combine ML with computational mechanics and numerical methods to create physics-informed models that improve accuracy and efficiency of simulations, in a hybrid work setting encouraging collaboration.

Qualifications

• PhD in computational mechanics, mechanical engineering, applied mathematics, computational science, physics or related field.
• Demonstrated experience with physics-informed machine learning or data-driven modeling.
• Ability to work in a multidisciplinary environment and communicate technical information clearly.

Responsibilities

• Develop physics-informed ML methods for computational mechanics and simulations.
• Integrate governing equations and material constraints into ML models and validate results.
• Publish findings in peer-reviewed journals and present at conferences.

Skills

Physics-informed ML

Computational mechanics

Numerical methods

Scientific ML

Independent research

Education

PhD in computational mechanics

Tools

Python

PyTorch

JAX

TensorFlow

High-performance computing

Job description

Lawrence Livermore National Laboratory is seeking a Physics-Informed Machine Learning Postdoctoral Researcher to develop and apply advanced computational methods for modeling complex physical systems.

You will combine ML with computational mechanics and numerical methods to create physics-informed models that improve accuracy and efficiency of simulations, in a hybrid work setting encouraging collaboration.