Post Doc Res Assoc

Overview

The Kahlert School of Computing at the University of Utah invites applications for a 1-year post-doctoral researcher to work on interdisciplinary research spanning machine learning, applied mathematics, computer science, and material sciences with a heavy software development component. The successful candidate will apply ML techniques to the finite element method (FEM) in composites and nonlinear materials (dry fibers) and will collaborate with AFRL and ARCTOS to integrate research into an existing JAX FEM framework developed jointly by University of Utah, AFRL, and ARCTOS.

About time allocation: 9 months at the University of Utah under supervision of Professors Varun Shankar and Robert M. Kirby, and 3 months on-base at AFRL with ARCTOS/AFRL, continuing collaboration with the University of Utah. Successful candidates may continue with ARCTOS as a research scientist.

Salary Range: $60K - $70K for post-doctoral funding depending on experience, with additional benefits.

• Contribute to the development of a hybrid software framework for the finite element method and machine learning within the JAX Python library, including efficient implementations of classical numerical algorithms.
• Extend the hybrid FEA-ML framework to include nonlinear cohesive zone models with simple traction-separation laws in a modular way to allow future addition of further traction-separation laws.
• Further extend the framework toward discrete damage modeling via extended finite element methods, leveraging existing and actively developed AFRL libraries related to crack growth.
• Use the hybrid FEM-ML framework to demonstrate a machine-learned crack model using rich experimental data, with inputs including material information at a resolution coarser than the mesh and an FEA-predicted stress field, and outputs indicating crack initiation or direction of crack growth.
• Contribute to the framework to support the simulation of dry-fiber mechanics, including relevant physics and contact, as identified by AFRL, and implement algorithms and solvers for distributed GPU computing in the JAX library.

The Kahlert School of Computing seeks a highly capable, self-motivated candidate able to work with minimal supervision in a multidisciplinary environment. Backgrounds in engineering, applied mathematics, physics, or computational sciences will be considered. Ideal candidates are comfortable with machine learning, the JAX library, finite element methods, and high-performance computing; material science knowledge is a plus. A long-term opportunity with ARCTOS after this 1-year position is encouraged but not required.

How to apply:

Contact Prof. Varun Shankar (shankarh.edu) and send all applications to both Prof. Shankar and Mr. Chris Coleman (chris.coleman).

Other notes:
Being self-motivated and having good organizational, communication, and teamwork skills is essential.

U.S. citizenship is required.

Requisition Number: PRN
43607B
Full Time

Location:

Campus
Department: 00062 - School of Computing
Pay Rate Range: 30000 to 75000
Close Date: 3/31/2026
Open Until Filled:
Yes