AI Security Intern at Actian in Remote

Summary: Actian is a trusted leader in data management, integration, and analytics, dedicated to helping businesses unlock the full potential of their data. The AI Security Intern will support the evaluation and secure adoption of enterprise AI technologies, focusing on large language models and cloud-based platforms, while contributing to research and the development of security controls for AI governance. Responsibilities: - Develop a foundational understanding of AI/ML concepts, large language models, and enterprise AI use cases, including data privacy and governance considerations - Research and analyze AI security threats such as prompt injection, data leakage, and model misuse, aligning findings with frameworks like OWASP Top 10 for LLMs - Gain hands-on experience with AWS Bedrock by testing multiple foundation models, evaluating outputs, and documenting behavior across use cases - Design and implement AI security controls, including guardrails, input/output validation, and monitoring strategies to mitigate risk - Capstone Project: Conduct end-to-end AI red team vs. blue team testing in AWS Bedrock, develop security recommendations, and deliver a final presentation including guardrail configurations, incident analysis, and an AI Acceptable Use Policy for the organization Required Qualifications: - Must be actively enrolled in a college degree program - Must be legally authorized to work in the United States Preferred Qualifications: - Pursuing a degree in Computer Science, Cybersecurity, Information Systems, or a related technical field - Foundational knowledge of cloud platforms (AWS preferred) and general security concepts - Exposure to AI/ML concepts such as LLMs, prompt engineering, or data privacy principles - Interest in cybersecurity, particularly emerging domains like AI/LLM security and adversarial testing - Strong analytical, research, and communication skills with the ability to present technical findings to diverse audiences Required Skills: AI security, Large language models (LLMs), Cloud platforms - AWS, AI/ML concepts, Security controls design, Threat analysis, OWASP Top 10 for LLMs, Adversarial testing, Data privacy, Incident analysis, Analytical skills, Research skills Benefits: Opportunity to travel – we will fly you out for onsite orientation at our Austin, Texas office location!