Intern, R&D Graduate Summer - Deep Reinforcement Learning, Remote

What Your Job Will Be Like

We are seeking a highly motivated graduate R&D intern candidate to conduct research involving the use of Deep Reinforcement Learning (DRL) within the context of developing optimal domain decomposition strategies to inform hybrid multi-scale coupling. You will join a highly interdisciplinary team conducting high-level R&D in solid mechanics, structural dynamics, hypersonics, numerical methods development and model order reduction.

A strong background in partial differential equation- (PDE-) based modeling and simulation (mod/sim), adaptive mesh refinement and DRL is a necessity.

Experience with domain decomposition-based coupling methods is a plus.

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

* Design, implement and test a DRL framework for guiding optimal domain decomposition strategies.

* Design, implement and test a DRL framework for guiding on-the-fly switching between reduced order models (ROMs) and high-fidelity models within a multi-scale domain decomposition framework.

* Perform theoretical analyses of novel coupling and adaptation algorithms.

* Program and test new and existing algorithms.

* Engage with the community for conferences, workshops, proposals and outreach.

* Develop and support open-source research software packages.

* Publish research results in high-quality journals and competitive conference venues.

The selected applicant can be a remote worker located in any U.S. State or District of Columbia. Regular or periodic travel to your assigned work location may be required.

Salary Range

At Sandia, we value the important work done by our interns and its contribution to National Security. Because of this, our interns earn competitive pay rates. Our pay structure is based on earned credit hours, classification, and degree level. Your pay rate will be determined during the hire process and included in your offer package. You can view the Intern Pay Rate chart here.

Qualifications We Require

You bring the confidence and skills to be eligible for the job by meeting these minimum requirements:

* Earned bachelor's degree

* Currently attending and enrolled full time in the spring term immediately preceding the internship (or scheduled to graduate in the spring) in an accredited science, engineering, or math graduate program

* Minimum cumulative GPA of 3.0/4.0

* Ability to work up to 40 hours per week during the summer

* To be eligible for this position, applicants must be legally authorized to work in the United States of America, Sandia will not sponsor work authorization for this position

Note:

If you have not yet started your graduate program, please apply to an undergraduate intern position.

Qualifications We Desire

* Pursuing a PhD in computer science, mathematics, mechanical engineering, applied mathematics, computational science, civil engineering or other relevant field.

* Experience with DRL, PDE-based mod/sim and adaptive mesh refinement.

* Experience in a common programming language such as Python.

* Experience with non-intrusive Operator Inference (OpInf) ROMs.

* Experience with the Schwarz alternating method for multi-scale coupling.

Posting Duration

This posting will be open for application submissions for a minimum of seven (7) calendar days, including the 'posting date'. Sandia reserves the right to extend the posting date at any time.

About Our Team

The Quantitative Modeling and Analysis Department conducts research, development, and systems engineering in computer science and engineering to address important, complex national security problems. Key research areas include uncertainty quantification, optimization, inference modeling, data analysis, and algorithm development. Much of our application development work focuses on verification, validation and uncertainty quantification of complex problems. We provide trusted design and software development for large, operations software as well as detailed scientific computing software.

The work is focused on providing efficient, validated information and technologies for use in predictive modeling and decision making.

About Sandia

Sandia National Laboratories is the nation's premier science and engineering lab for national…