AI Penetration Testing Intern - Summer 2026

• United States of America - North Carolina - Morrisville

As an AI Penetration Testing Intern, you will gain hands‑on experience helping secure AI‑powered applications, with a focus on systems built using Large Language Models (LLMs). This role is designed for early‑career undergraduate students who are curious about AI security, ethical hacking, and emerging technologies.

You will learn how security teams proactively test AI systems for weaknesses by simulating real‑world attacks, identifying risks unique to Generative AI, and helping improve the safety and reliability of AI products. Working alongside experienced security and AI engineers, you’ll build practical skills in red teaming, risk assessment, and technical documentation while contributing to meaningful security initiatives.

What You’ll Do

With mentorship and guidance, you will:

• Learn how to test and evaluate the security of LLM‑based applications, including chatbots, agents, and AI‑enabled tools.
• Assist in applying structured AI red‑teaming approaches, frameworks, and playbooks to help identify potential vulnerabilities.
• Help design and execute adversarial testing scenarios focused on GenAI‑specific risks, such as:
• Prompt injection and multi‑turn manipulation
• Misuse of tools or plugins connected to LLMs
• Data poisoning or unsafe content generation
• Support security risk assessments by documenting findings and contributing to mitigation recommendations.
• Create clear, well‑organized documentation, such as test cases, reports, and example attack scenarios.
• Research and stay up to date on emerging AI security risks, trends, and best practices.
• Collaborate with cross‑functional teams to help strengthen the security of AI products.

Basic Qualifications

• Currently pursuing a Bachelor’s degree in Computer Science, Cybersecurity, Information Security, Data Science, or a related technical field.
• Foundational understanding of programming concepts and computer systems.
• Interest in AI, machine learning, security, or ethical hacking.
• Strong problem‑solving and analytical skills, with attention to detail.
• Ability to work both independently and collaboratively in a team environment.
• Professional mindset with respect for confidentiality and sensitive information.

Preferred Qualifications

• Coursework or projects related to:
• Machine learning or artificial intelligence
• Cybersecurity, penetration testing, or threat modeling
• Familiarity with LLM concepts such as prompting, chatbots, or AI agents.
• Experience writing technical documentation, reports, or project summaries.
• Curiosity about how AI systems can fail—and how to make them safer.

• United States of America - North Carolina - Morrisville