APPLICATION INSTRUCTIONS:

• CURRENT PENN STATE EMPLOYEE (faculty, staff, technical service, or student), please login to Workday to complete the internal application process. Please do not apply here, apply internally through Workday.

• CURRENT PENN STATE STUDENT (not employed previously at the university) and seeking employment with Penn State, please login to Workday to complete the student application process. Please do not apply here, apply internally through Workday.

• If you are NOT a current employee or student, please click “Apply” and complete the application process for external applicants.

 

Approval of remote and hybrid work is not guaranteed regardless of work location. For additional information on remote work at Penn State, see Notice to Out of State Applicants.

 

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.

Compensation:

The starting rate for this job is $18, 20 hours/week.

 

BACKGROUND CHECKS/CLEARANCES

Employment with the University will require suc