Graduate (10-12 weeks) Intern - AI/ML for Cybersecurity

National Laboratory of the Rockies • Golden, CO

9d • $51,200 - $81,900 • Onsite

About The Position

The intern will conduct hands-on research at the intersection of machine learning, statistics, and critical energy infrastructure security. The position focuses on improving the reliability, transparency, and operator-readiness of AI-driven cybersecurity tools used to secure power grid substations and physical assets, particularly through explainability and robust uncertainty bounds.

The work includes designing and implementing explainable AI methods, applying statistical methods to quantify model confidence and predictive uncertainty, and analyzing cyber-physical power system security datasets to understand feature patterns and validate anomaly-detection behavior. The intern will also explore machine-learning safety techniques to improve predictable model behavior under distribution shifts or input corruption, support visualization and alert design for operators, and collaborate with cybersecurity researchers and AI development teams to integrate explainability modules, document results, and develop deployment guidelines.

This is a 10–12-week graduate internship in Golden, Colorado, with a stated schedule of 40 hours per week. Applicants must meet the applicable student or recent-graduate education criteria and the listed academic, programming, and research qualifications. The anticipated application submission window is up to 30 days and may be extended. The annualized salary range for the Graduate job profile is $51,200–$81,900, based on full-time work of 40 hours per week.

Requirements

• Minimum cumulative GPA of 3.0.
• For the graduate student pathway, be enrolled full-time in a master’s degree program at an accredited institution; alternatively, the posting allows eligible recent graduates and graduate/PhD pathways as specified in its basic qualifications.
• Currently pursuing or completed a Bachelor’s, Master’s, or Ph.D. in Computer Science, Cybersecurity, Electrical Engineering, AI, Applied Mathematics, or Statistics.
• Strong proficiency in Python.
• Hands-on experience with PyTorch, TensorFlow, or Hugging Face.
• Substantial coursework or project experience in Explainable AI (XAI), machine-learning safety, confidence calibration, or statistical uncertainty modeling.
• Practical experience working with Large Language Models (LLMs), Foundation Models, or other complex deep neural networks.
• Applicants are responsible for uploading official or unofficial school transcripts; if selected, a letter of recommendation is required.
• Must meet educational requirements before the employment start date.

Nice To Haves

• Active research or publications in top-tier conferences such as NeurIPS, ICML, ICLR, AAAI, IEEE S&P, USENIX Security, or ACM CCS, focused on XAI, robust machine learning, or cyber-physical energy systems.
• Experience with specialized explainability libraries such as Captum, SHAP, or LIME, and uncertainty calibration methods.
• Familiarity with multi-sensor data fusion, power systems modeling, or grid anomaly detection.
• Contributions to open-source software libraries focused on AI transparency, reliability, or security.

Responsibilities

• Design and implement explainable AI methods, such as attribution maps, rule extraction, and root-cause analyses, to make complex machine-learning models transparent and auditable for control-room operators and system administrators.
• Apply statistical techniques and frameworks, such as conformal prediction, Bayesian neural networks, or ensemble methods, to quantify model confidence and predictive uncertainty in real time.
• Analyze cyber-physical power system security datasets, including 9-Bus system baseline and cyber-physical anomaly runs, to identify feature patterns and validate anomaly-detection model behavior.
• Explore machine-learning safety techniques, including model steering, to support predictable model behavior under distribution shifts or input corruptions.
• Support research into visualization methods and alert design that clearly present explainability and confidence metrics and assist operators with alert prioritization.
• Collaborate with cybersecurity researchers and AI development teams to integrate explainability modules, document results, and compile guidelines for deploying reliable AI models.

Benefits

• Medical insurance
• Dental insurance
• Vision insurance
• 403(b) Employee Savings Plan with employer match
• Sick leave where required by law
• Potential eligibility for performance-, merit-, and achievement-based monetary awards
• Some positions may be eligible for relocation expense reimbursement

What This Job Offers

• Job Type: Full-time
• Career Level: Intern