Research Associate - School of Computer Science - S3D

Carnegie Mellon University•Pittsburgh, PA

3d•Onsite

About The Position

Carnegie Mellon University's Software and Societal Systems Department (S3D), in the School of Computer Science (SCS), has two part-time research associate openings. These roles will focus on an interdisciplinary project aimed at modeling and mitigating risks introduced by agentic AI in enterprise environments. This position is ideal for someone with a background in Responsible AI, AI Governance, Cybersecurity and Privacy, and experience with Agentic AI technologies. Agentic AI systems, capable of autonomous task execution and decision-making, are increasingly used in workplaces for tasks like scheduling, report generation, and system access. While offering productivity benefits, they also introduce new system-level risks beyond traditional model concerns, involving complex interactions between tools, data, users, and external services. The project aims to answer two key research questions: 1. How does agentic AI (autonomy, tool use, multi-step planning) alter traditional cybersecurity and privacy threat models in enterprises? 2. What technical and governance mechanisms are most effective for mitigating these risks while maintaining human oversight?

Requirements

Bachelor’s degree in computer science required
1-3 years of research experience required
Strong background in Privacy and Security
Strong organization and communication skills necessary
Experience with Responsible AI, including Agentic Technology
Experience collaborating with others in the context of research projects
Successful completion of a pre-employment background check

Nice To Haves

Master’s degree in computer science preferred
Experience in HCI and/or threat modeling would be a plus
A combination of education and proven experience from which comparable knowledge is demonstrated may be considered

Responsibilities

Combine the development of threat and failure taxonomies for agentic AI in the enterprise
Development and simulation of synthetic workflows
Failure mode analysis
Development and evaluation of mitigation strategies
Identification/development of relevant metrics
Develop a framework that can provide actionable guidance to enterprises
Capable of working under limited supervision
Effectively interact with a varied population of internal and external partners at a high level of integrity