AI-Driven Materials Automation Intern

Battelle Energy Alliance; Idaho Falls (ID); Sur place; USD 51 000 - 57 000; Plein temps

Avantages offerts par ce poste

Paid holiday time off

Travel reimbursement

Résumé du poste

Idaho National Laboratory (INL) seeks a PhD intern to help develop an automated platform that combines nanoindentation, tensile testing, DIC, and EBSD for mechanical property research. You will design intelligent decision-making algorithms that adapt testing conditions in real time using Bayesian optimization and GP surrogates.

The role emphasizes CNN-based interpretation, active learning, and integration with autonomous experimental platforms within the SPL at the MFC.

Qualifications

• Enrolled full time in a PhD program studying Computer Science, Artificial Intelligence, Machine Learning, or Data Science.
• Minimum overall GPA 3.0.
• Authorization to work in the U.S. (including CPT and OPT).
• Current Resume or CV.
• Unofficial Transcripts (include current and completed degree programs).
• Current class schedule and number of credits.

Responsabilités

• Support development of an integrated autonomous platform for testing mechanical properties.
• Develop intelligent decision-making algorithms to dynamically guide additional testing.
• Leverage Bayesian optimization with GP surrogate models for adaptive experimental design.
• Apply active learning and CNNs for real-time interpretation of nanoindentation and DIC/EBSD datasets.

Connaissances

Bayesian optimization

Gaussian processes

CNNs for image data

Active learning

DIC familiarity

EBSD familiarity

Autonomous platforms

Formation

PhD student in CS/AI/ML/Data Science

Description du poste

Idaho National Laboratory (INL) seeks a PhD intern to help develop an automated platform that combines nanoindentation, tensile testing, DIC, and EBSD for mechanical property research. You will design intelligent decision-making algorithms that adapt testing conditions in real time using Bayesian optimization and GP surrogates.

The role emphasizes CNN-based interpretation, active learning, and integration with autonomous experimental platforms within the SPL at the MFC.