Senior Researcher, Agentic AI Security

Job Description
We are seeking a highly motivated and talented research scientist working in natural language processing (NLP), machine learning (ML), or/and Artificial Intelligence (AI) to join our Data and Security Lab at Pittsburgh. This pivotal role will focus on endowing AI multi-agent systems with advancing foundational security technologies like safety, privacy-preserving, alignment, authentication, and authorization. We value individuals with a vision to pick up new knowledge, see through complex scenarios and arrive at simple, elegant yet workable solutions. Self-driven nature, creativity, communication skills, and attention to details are traits of a successful researcher in this role.

Job Responsibilities

• Join us by the end of December 2025
• Conduct research on developing novel security and safety technologies for multi-agent systems like threat modeling, vulnerability monitoring, agentic safety check and agentic guardrails
• Conduct experiments and data analysis to evaluate the effectiveness of research findings on synthetic simulations and real word applications
• Publish findings in renowned scientific journals and conferences, while also showcasing achievements through presentations at invited talks, conferences, and workshops
• Integrate various stages of technologies from early stage in-house developed to commercially available software to develop impactful solutions
• Foster collaboration across interdisciplinary teams, including esteemed professors, to propel research endeavors forward

Essential Requirements

• PhD in Computer Science, a related field, or equivalent practical experience
• Strong track record of publishing research in top-tier conferences and journals on AI, ML, NLP, or Security
• Expert-level knowledge and extensive experience in one or more these areas: LLM-based multi-agent systems, security for agent, agent for security, agentic reinforcement learning, and self-evolving multi-agent orchestration and collaboration
• Proven Experience in rapid prototyping and testing methodologies to validate the functionality and performance of developed solutions

Preferred Requirements

• Proficiency in NLP and ML programming written in Python or/and web frontend programming written in TypeScript
• Design and prototype applications combining a variety of tools and platforms
• Experience in integrating multiple technologies from multiple research domains including AI, ML, NLP and security
• Experience in interdisciplinary research collaborations

Compétences idéales

• Authentication
• Threat Modeling

• Pittsburgh, Pennsylvania, United States

Expérience professionnelle

• Machine Learning
• NLP
• Cyber Security Specialist

Compétences linguistiques

• English