Assistant AI Security Researcher

Carnegie Mellon University • Pittsburgh, PA

21h

About The Position

The CERT Division of Carnegie Mellon University's Software Engineering Institute (SEI) is seeking an Assistant AI Security Researcher to advance research in AI security. As part of the Threat Analysis Directorate, the researcher will work with security experts on challenges including vulnerability discovery and assessment for AI systems, evaluation of defenses and mitigations, reverse engineering AI systems and models, and identifying emerging research needs. The role involves collaborating with network defenders, software developers and vendors, security researchers, AI practitioners, and policymakers; co-authoring technical proposals; conducting research; and presenting findings and recommendations to Department of Defense sponsors, government and industry decision makers, and academic conferences.

The researcher will develop approaches for analyzing AI system robustness and apply them to understand vulnerabilities and attacker techniques. They will reverse engineer malicious code, design analysis methods and tools, assess industry and research-community tools and processes, and help identify and address complex threats. The role also includes studying and influencing AI security and vulnerability disclosure ecosystems; developing models, tools, and datasets to characterize AI threats and vulnerabilities; publishing findings; supporting testing, evaluation, and transition of government-funded technologies; and identifying ways to apply AI to cybersecurity research.

The position is based in Pittsburgh, Pennsylvania. Occasional travel to SEI and CMU locations, sponsor sites, conferences, and offsite meetings is expected (approximately 5%). Employment is regular, full-time staff. The successful candidate will undergo a background check and must obtain and maintain a Department of Defense security clearance.

Requirements

• Bachelor of Science degree in machine learning, cybersecurity, statistics, or a related discipline.
• Interest in AI/ML and cybersecurity, intellectual curiosity, and a desire to make an impact beyond the organization.
• Practical experience applying cybersecurity knowledge to vulnerability research, analysis, disclosure, or mitigation.
• Familiarity with implementing and applying AI/ML techniques to practical problems.
• Familiarity with common AI/ML software packages and tools, such as NumPy, PyTorch, TensorFlow, or ART.
• Knowledge of or familiarity with reverse engineering tools, such as NSA Ghidra or IDA Pro.
• Experience with Python, C/C++, or low-level programming.
• Experience developing frameworks, methodologies, or assessments to evaluate the effectiveness and robustness of technologies.
• Excellent oral and written communication skills, particularly in technical communications with non-experts.
• Ability to travel occasionally, approximately 5%.
• Must pass a background check and obtain and maintain a Department of Defense security clearance.
• Applicants with strong technical proficiency in either AI/ML or cybersecurity may apply if they demonstrate intellectual agility and commitment to accelerated learning.

Responsibilities

• Develop state-of-the-art approaches for analyzing the robustness of AI systems.
• Apply analysis approaches to understand AI system vulnerabilities and how attackers adapt their tradecraft to exploit them.
• Reverse engineer malicious code in support of high-impact customers.
• Design and develop new analysis methods and tools.
• Identify and address emerging and complex threats to AI systems and participate in the broader security community.
• Study and influence AI security and vulnerability disclosure ecosystems.
• Evaluate the effectiveness of tools, techniques, and processes developed by industry and the AI security research community.
• Uncover and shape assumptions underlying current best practices in AI security.
• Develop thought models, tools, and datasets to characterize threats to and vulnerabilities in AI systems, and publish results.
• Use research results to support testing, evaluation, and transition of technologies developed by government-funded research programs.
• Identify opportunities to apply AI to improve existing cybersecurity research.
• Co-author technical proposals, execute research, and present findings and recommendations to sponsors, decision makers, and academic conferences.
• Travel occasionally to SEI and CMU locations, sponsor sites, conferences, and offsite meetings.

Benefits

• 8% monthly retirement contribution without requiring an employee contribution.
• Tuition benefits at CMU and other institutions for employees and their dependent children.
• Flexible work arrangements.
• Paid parental leave.
• Paid military leave.
• Annual professional development opportunities, including conferences, training, and certifications.
• Reimbursement for professional society memberships.
• Relocation assistance.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level