Digital Twin Intern

Southern Arkansas University; Idaho Falls (ID); On-site; USD 34,000 - 55,000; Full time

Job summary

A leading research institution is seeking a graduate student for a Summer 2026 internship in Nuclear Engineering. The role involves developing AI and machine learning methods to enhance digital twin-based supervisory control systems. Candidates should be enrolled in a Ph.D. program with strong analytical skills and familiarity with Python. This internship offers hands-on research experience, with a flexible start date and a unique schedule allowing for every other Friday off. Course credit may also be available.

Qualifications

• Enrolled full time in a Ph.D. program in Nuclear Engineering or a closely related field.
• Minimum 3.0 GPA and authorization to work in the U.S. (including CPT/OPT).
• Coursework or experience in modeling & simulation, machine learning, verification & validation, and uncertainty quantification.
• Familiarity with Python and strong analytical skills.

Responsibilities

• Integrate active learning, reinforcement learning, and multi-agent AI systems into a digital twin framework.
• Design and implement methods for discrepancy detection and diagnosis.
• Analyze simulation and sensor data, develop ML models in Python.
• Analyze simulation and sensor data, develop ML models in Python, and contribute to technical reports and publications.

Skills

Reinforcement learning

Active learning

Digital twins

Machine learning

Analytical skills

Education

Ph.D. program in Nuclear Engineering or related field

Tools

Python

Digital twin

Time-series data analysis

Job description

⚛️ Advance the Future of Nuclear Energy with INL!

Idaho National Laboratory (INL) is seeking a graduate student in Nuclear Engineering (or a closely related field) for a Summer 2026 internship to help develop a discrepancy checking and diagnosis tool for a digital‑twin–based supervisory control system. This is a hands‑on research opportunity to apply AI and machine learning methods to next‑generation energy systems.

Responsibilities

• Integrate active learning, reinforcement learning, and multi‑agent AI systems into a digital twin (DT) framework.
• Design and implement methods for discrepancy detection and diagnosis within a DT‑based supervisory control loop.
• Apply verification, validation, and uncertainty quantification (VVUQ) to evaluate model fidelity and decision robustness.
• Analyze simulation and sensor data, develop ML models in Python, and contribute to technical reports and publications.

Enrolled full time in a Ph.D. program in Nuclear Engineering or a closely related field.

Coursework or experience in modeling & simulation, machine learning, verification & validation, and uncertainty quantification.

Familiarity with Python and strong analytical skills.

Minimum 3.0 GPA and authorization to work in the U.S. (including CPT/OPT).

Preferred Qualifications

• Experience with reinforcement learning, active learning, digital twins, or advanced control systems.
• Comfort with time‑series/sensor data and data–model discrepancy analysis.
• Excellent written and verbal communication skills and a passion for collaborative research.

📍 Onsite at INL – Idaho Falls, ID
🗓️ Summer 2026 | Flexible start date
🕘 9x80 schedule (every other Friday off)
🎓 Doctoral-level internship | Course credit may be available

Join us and help shape the future of AI‑driven nuclear control systems through cutting‑edge digital twin research.