College of IST Privacy/Security in LLM-Driven Agentic Systems PhD Internship w/ Dr. Sharma

JOB DESCRIPTION AND POSITION REQUIREMENTS

The College/Unit of IST is seeking applicants for part-time job of Privacy/Security in LLM-Driven Agentic Systems PhD Internship w/ Dr. Sharma

About the Project:

Governance, Privacy and Security Lab is conducting research at the intersection of security, privacy, and AI systems design. The goal of this project is to create a structured analysis of information flow in modular, LLM-driven agentic systems. The focus is on identifying security, privacy, and control failures that emerge when autonomous modules interact across loosely enforced system boundaries. We also would like to estimate the value of privacy and security in the agentic systems from users perspective.

Internship Role:

We are seeking a highly motivated PhD intern (part-time research role) to support the development of tools, models, and taxonomies that expose and mitigate vulnerabilities in LLM-driven agentic systems. You will work closely with team to:

• Analyze modular architectures for unanticipated information flow
• Formalize information flow motifs and their associated threat vectors
• Assist in developing a layered threat model aligned with NIST Cybersecurity Framework principles
• Apply causal tracing, influence tracking, and behavioral audit techniques to real-world agentic systems
• Contribute to an academic paper and open-source tools

Qualifications:

• Enrolled in a PhD program in Computer Science, Information Science, Cybersecurity, or related fields
• Research experience in one or more of the following: LLMs, multi-agent systems, privacy/ security
• Analytical and writing skills
• Experience with LLM agent frameworks or security auditing tools is a plus

Apply:

Please apply to the position to be considered. Please upload a CV, and a sample publication or writing sample. Applications are reviewed on a rolling basis.