AI Security Research Intern

About the Role

You will work as a part of the Threat Analysis Directorate within CERT at the Software Engineering Institute (SEI) | Carnegie Mellon University. You will collaborate with security experts focused on advancing the state of the art and practice for analyzing, assuring, and countering software systems to enhance National Security.

Key Responsibilities

• Investigate and evaluate AI systems to contribute to core functions: AI Assurance, Red Teaming of AI Systems, and AI Digital Forensics, Response, and Mitigation.
• Take part in project reviews to gather feedback on research and analysis approaches.
• Revise work products, provide thorough documentation, and present findings.
• Help to develop solutions to solve operational and mission-based challenges.
• Job Function Breakdown:
• AI Security Research and Development: 80%
• Documentation of Results: 20%

Requirements & Tech Stack

• Enrolled in a degree-granting program.
• Able to work onsite at the SEI Pittsburgh office 5 days a week during the summer internship.
• Must be eligible to work in the United States without Visa sponsorship.
• Subject to a background check.
• Solid understanding of AI/ML including Generative AI.
• Basic proficiency with a programming language, preferably Python.
• Familiarity with common AI/ML software packages and tools (e.g., PyTorch, TensorFlow).

Qualifications

• Excellent written and verbal communication.
• Ability to critically think and problem solve.
• Ability to collaborate internally and externally with professional engineers and researchers.
• Willingness to learn new technologies with cross-functional teams.
• Desired Experience:
• Experience with programming languages (preferably Python).
• Experience with training AI/ML models.
• Experience with adversarial machine learning techniques.
• Experience with red-teaming cyber and/or AI systems.
• Basic understanding of cybersecurity concepts.
• Experience with clearly documenting and communicating findings.