AI Security Researcher

About the Role

The CERT Division of the Software Engineering Institute (SEI) is seeking an AI Security Researcher to pioneer research in the emerging area of AI security. Originally established in response to the Morris worm in 1988, CERT remains a leader in cybersecurity research, improving software robustness and addressing sophisticated threats. This role focuses on ensuring the security and robustness of AI systems, collaborating with security experts to advance AI security at national and global scales.

As part of the Threat Analysis Directorate, you will work on vulnerability discovery, assessments, and defenses for AI systems, reverse engineering, and identifying new research areas. You’ll collaborate with elite professionals, university faculty, and government representatives to shape national AI security strategy, co-author research proposals, execute studies, and present findings to sponsors and decision-makers.

Responsibilities

• Develop state-of-the-art approaches for analyzing the robustness of AI systems.
• Apply these approaches to understand vulnerabilities in AI systems and how attackers exploit them.
• Reverse engineer malicious code, design and develop new analysis methods and tools, and address emerging threats to AI systems.
• Study and influence the 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 fundamental assumptions underlying current best practices in AI security.
• Develop thought models, tools, and datasets to characterize threats and vulnerabilities in AI systems, and publish findings.
• Use research results to aid in testing, evaluating, and transitioning technologies from government-funded programs.
• Identify opportunities to apply AI to improve existing cybersecurity research.

Qualifications

• BS in machine learning, cybersecurity, statistics, or a related discipline with eight (8) years of experience; OR MS in the same fields with five (5) years of experience; OR PhD in the same fields with two (2) years of experience.
• Deep interest in AI/ML and cybersecurity, with intellectual curiosity and a desire to make an impact beyond your organization.
• Practical experience applying cybersecurity knowledge to vulnerability research, analysis, disclosure, or mitigation.
• Experience advising on security topics based on research and expert opinion.
• Familiarity with implementing and applying AI/ML techniques to solve practical problems.
• Familiarity with common AI/ML software packages and tools (e.g., NumPy, PyTorch, TensorFlow, ART).
• Knowledge or familiarity with reverse engineering tools (e.g., NSA Ghidra, 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 communication skills (oral and written), particularly for technical communications with non-experts.
• Enjoy mentoring, cross-training, and sharing knowledge within the broader community.
• Candidates with strong technical proficiency in either AI/ML or cybersecurity are welcome, provided they demonstrate intellectual agility and a commitment to accelerated learning.

You must be able to travel occasionally (5%) to support the SEI’s mission and obtain/maintain a Department of War (DoW) security clearance.

Benefits

• 8% monthly retirement contribution (no employee contribution required).
• Tuition benefits for you and your dependent children at CMU and other institutions.
• Flexible work arrangements and paid parental/military leave.
• Annual professional development opportunities, including conference attendance, training, and certification reimbursement.
• Relocation assistance.
• Work with cutting-edge technologies and a world-class team to solve national security challenges.