Postdoctoral Appointee — SciML for Impactful Simulations

Sacbar; Livermore (CA); On-site; USD 70,000 - 110,000; Full time

Benefits offered by this job

Flexible work arrangements

Relocation assistance

Solid work/life balance

Job summary

Sandia National Laboratories seeks a Postdoctoral Appointee to advance trustworthy scientific machine learning (SciML) and data-driven analysis for computational science applications. You will develop ML surrogates and reduced-order models within physics-based simulations, and lead verification and uncertainty quantification studies.

Work onsite in Livermore, CA, collaborating with PIs and partners to benchmark methods against high-fidelity models.

Qualifications

• PhD (conferred within five years) in applied mathematics, computational science, engineering, statistics, computer science, or a related field.
• Expertise in machine learning, scientific machine learning, uncertainty quantification, or statistical learning.
• Experience developing or evaluating ML methods for simulation, image, signal, or high-dimensional data.

Responsibilities

• Develop and evaluate ML-based surrogates, reduced-order models, and embedded data-driven components within physics-based simulations.
• Design and execute verification, validation, uncertainty quantification, robustness testing, explainability, and interpretability studies.
• Apply feature-extraction and pattern-recognition methods to images, microstructures, sensor data, and high-dimensional outputs.
• Collaborate with Sandia PIs, national laboratories, and academic partners to benchmark data-driven methods against high-fidelity models and experiments.

Skills

Machine Learning

SciML

Uncertainty Quantification

Statistical Learning

Education

PhD (conferred within 5 years) in applied mathematics, computational science, engineering, statistics, computer science, or a related field

Tools

PyTorch

JAX

TensorFlow

scikit-learn

NumPy

SciPy

pandas

PyWavelets

OpenCV

Job description

Sandia National Laboratories seeks a Postdoctoral Appointee to advance trustworthy scientific machine learning (SciML) and data-driven analysis for computational science applications. You will develop ML surrogates and reduced-order models within physics-based simulations, and lead verification and uncertainty quantification studies.

Work onsite in Livermore, CA, collaborating with PIs and partners to benchmark methods against high-fidelity models.