AI Security Research Intern – Summer 2027

Carnegie Mellon University•Pittsburgh, PA

12d•Onsite

About The Position

The AI Security Research Intern will work within the Threat Analysis Directorate of CERT at the Software Engineering Institute (SEI), collaborating with security experts to advance methods for analyzing, assuring, and countering software systems in support of national security. The intern will investigate and evaluate AI systems in support of AI assurance, AI red teaming, and AI digital forensics, response, and mitigation. They will participate in project reviews, incorporate feedback through revisions, document and present work products, and help develop solutions to operational and mission-based challenges. The position is onsite at the SEI Pittsburgh office five days per week and is available during the summer of 2027.

Requirements

Be enrolled in a degree-granting program.
Be eligible to work in the United States without visa sponsorship and be subject to a background check.
Be able to work an internship during the summer.
Be able to work onsite at the SEI Pittsburgh office five days per week.
Have excellent written and verbal communication skills.
Be able to think critically and solve problems.
Have a solid understanding of AI/ML, including generative AI.
Have basic proficiency with a programming language, preferably Python.
Be familiar with common AI/ML software packages and tools, such as PyTorch or TensorFlow.
Be able to collaborate with professional engineers and researchers internally and externally.
Be willing to learn new technologies with cross-functional teams.

Nice To Haves

Experience with programming languages, preferably Python.
Experience training AI/ML models.
Experience with adversarial machine learning techniques.
Experience red-teaming cyber and/or AI systems.
Basic understanding of cybersecurity concepts.
Experience clearly documenting and communicating findings.

Responsibilities

Investigate and evaluate AI systems for AI assurance, red teaming, and AI digital forensics, response, and mitigation.
Participate in project reviews and gather feedback on research and analysis approaches.
Revise, thoroughly document, and present work products.
Help develop solutions to operational and mission-based challenges.
Contribute to AI security research and development and document results.