AI-Enhanced Automation Intern - Summer 2027

Idaho National Laboratory•Idaho Falls, ID

2d•Onsite

About The Position

The AI-Enhanced Automation Intern will support development of an integrated, autonomous platform for testing mechanical properties. The platform combines nanoindentation and tensile testing with characterization using digital image correlation (DIC) and electron backscattered diffraction (EBSD), bringing multiple testing modes and length scales into a single automated workflow. Using real-time data from testing, the intern will help develop intelligent decision-making algorithms that recommend additional tests under varying conditions. Bayesian optimization with Gaussian process surrogate models will adaptively select experimental conditions, while active learning and convolutional neural networks (CNNs) will support real-time interpretation of nanoindentation and DIC datasets. The goal is to continuously optimize testing protocols and thoroughly probe material behavior. The work is conducted in the Structural Properties Laboratory (SPL) at the Materials and Fuels Complex (MFC) at Idaho National Laboratory (INL). The team works an onsite 4x10 schedule. Internship start date and duration vary based on the project and student availability.

Requirements

Be enrolled full time in a PhD program at an accredited college or university, studying Computer Science, Artificial Intelligence, Machine Learning, or Data Science.
Have a minimum overall GPA of 3.0.
Be authorized to work in the United States, including through CPT or OPT.
Provide a current resume or CV.
Provide unofficial transcripts that include current and completed degree programs.
Provide a current class schedule and number of credits.

Nice To Haves

Experience with Bayesian optimization and Gaussian process surrogate models for adaptive experimental design.
Experience developing or applying convolutional neural networks (CNNs) for image-based data interpretation.
Familiarity with active learning methods for real-time or iterative decision-making.
Exposure to materials characterization techniques such as nanoindentation, DIC, or EBSD, or to automated/autonomous experimental platforms, through coursework, research, or a prior internship.

Responsibilities

Support development of an integrated and autonomous platform for mechanical-property testing.
Help develop algorithms that use real-time testing data to recommend additional tests under varying conditions.
Use Bayesian optimization and Gaussian process surrogate models to adaptively select experimental conditions.
Support real-time interpretation of nanoindentation and DIC datasets using active learning and convolutional neural networks.
Contribute to optimization of testing protocols to thoroughly evaluate material behavior.