Postdoctoral Appointee - Scientific Machine Learning; SciML Physical & Materials Sciences, Onsite

Position: Postdoctoral Appointee - Scientific Machine Learning (SciML) for Physical & Materials Sciences, Onsite
About Sandia

Sandia National Laboratories is the nation's premier science and engineering lab for national security and technology innovation, with teams of specialists focused on cutting-edge work in a broad array of areas. Some of the main reasons we love our jobs:

* Challenging work with amazing impact that contributes to security, peace, and freedom worldwide

* Extraordinary co-workers

* Some of the best tools, equipment, and research facilities in the world

* Career advancement and enrichment opportunities

* Flexible work arrangements for many positions include 9/80 (work 80 hours every two weeks, with every other Friday off) and 4/10 (work 4 ten-hour days each week) compressed workweeks, part-time work, and telecommuting (a mix of onsite work and working from home)

* Generous vacation, strong medical and other benefits, competitive 401k, learning opportunities, relocation assistance and amenities aimed at creating a solid work/life balance
* World-changing technologies. Life-changing careers. Learn more about Sandia at: http://(Use the "Apply for this Job" box below)..gov

* These benefits vary by job classification.

What Your Job Will Be Like

We are seeking a Postdoctoral Appointee to join our AI and Computational Materials Science team at the Center for Integrated Nanotechnologies. This role is dedicated to the development and implementation of Scientific Machine Learning (SciML) frameworks to solve complex problems in materials reliability and physical sciences. You will work at the cutting edge of "AI-for-Science," bridging the gap between traditional governing equations (PDEs/ODEs) and modern deep learning architectures.

You will be responsible for designing AI-ready data pipelines that ingest heterogeneous data ranging from high-fidelity Molecular Dynamics (MD), Discrete Dislocation Dynamics, and Phase Field outputs to experimental microscopy and sensor streams to build predictive models for materials aging. This work requires being located (or relocating) in Albuquerque, New Mexico, to participate in our vibrant, interdisciplinary research community at Sandia National Laboratories and CINT.

On any given day, you may be called on to:

* Develop and deploy Physics-Informed Neural Networks (PINNs), Deep Operator Networks (DeepONets), or Fourier Neural Operators (FNOs) to accelerate materials simulations.

* Build and operate automated, AI-mediated ingestion pipelines for large-scale scientific datasets generated by HPC clusters and experimental instruments.

* Design surrogate models and digital twins that account for uncertainty quantification (UQ) in materials reliability and degradation.

* Implement high-performance ML workflows using PyTorch in a massively parallel computing environment.

* Collaborate with domain scientists, experimentalists, and infrastructure engineers to curate FAIR-compliant (Findable, Accessible, Interoperable, Reusable) datasets.

* Publish your research in premier AI and materials science journals and present at conferences such as NeurIPS, ICML, or MRS.

Due to the nature of the work, the selected applicant must be able to work onsite.

Qualifications We Require

* You have, or are pursuing, a PhD in Applied Mathematics, Computer Science, Applied Physics, Materials Science, or a related science/engineering field. PhD must be conferred within 5 years of employment.

* Demonstrated expertise in Scientific Machine Learning (SciML) specifically applied to physical, chemical, or materials science problems.

* Strong proficiency in PyTorch or equivalent deep learning frameworks for developing custom neural architectures.

* A significant track record of research excellence, evidenced by peer-reviewed publications and presentations in computational or data-driven science.

* Excellent written and verbal communication skills for collaborating in a multidisciplinary team environment.

Qualifications We Desire

* Experience in building and maintaining production-level data pipelines or scientific or engineering data.

* Knowledge of advanced AI-mediated data curation techniques, such as automated annotation, feature extraction, and dataset fingerprinting.

* Familiarity with version control for models and datasets.

* Experience with High-Performance Computing (HPC) and distributed training of large-scale models using frameworks like Horovod or PyTorch Distributed.

* Background in Uncertainty Quantification (UQ) and Bayesian inference within the context of physical modeling.

* Ability to work effectively in a dynamic environment, guiding technical decisions and contributing to the strategic growth of the group's AI portfolio.

About Our Team

Our department supports the Center for Integrated Nanotechnology (CINT). CINT is a Department of Energy/Office of Science Nanoscale Science Research Center operating as a national user facility devoted to establishing the scientific principles that govern the design, performance, and integration of nanoscale materials. Through its core facility in Albuquerque and gateway facility in Los Alamos, CINT provides users from…