AI Security Researcher: Threat Analysis & Research

Carnegie Mellon University; Pittsburgh (Allegheny County); On-site; USD 90,000 - 150,000; Full time

Benefits offered by this job

8% retirement contribution

Tuition benefits

Flexible work arrangements

Paid parental leave

Relocation assistance

Job summary

Carnegie Mellon University’s CERT Division at CMU SEI seeks an Assistant AI Security Researcher to advance AI security research at national and global scale. You will co-author proposals, execute research, and present results to DoD sponsors, industry, and conferences.

Join a team focused on robustness, vulnerability discovery, and novel defenses for AI systems, with opportunities to publish, travel, and collaborate across academia, industry, and government.

Qualifications

• BS in machine learning, cybersecurity, statistics or related discipline.
• Interest in AI/ML and cybersecurity with intellectual curiosity.
• Experience applying cybersecurity knowledge toward vulnerability research, analysis, disclosure, or mitigation.
• Familiarity with AI/ML software packages (Numpy, PyTorch, TensorFlow, ART).
• Experience with reverse engineering tools (Ghidra, IDA Pro).

Responsibilities

• Develop state of the art approaches for analyzing robustness of AI systems.
• Apply approaches to study vulnerabilities in AI systems and attacker tradecraft.
• Reverse engineer malicious code to support high-impact customers and develop new analysis methods.
• Study and influence AI security and vulnerability disclosure ecosystems.
• Evaluate tool effectiveness and improve AI security practices.
• Publish results and aid in transitions of government-funded technologies.
• Identify opportunities to apply AI to improve cybersecurity research.

Skills

AI/ML

Python

C/C++

Numpy

PyTorch

TensorFlow

ART

Communication skills

Education

BS in machine learning, cybersecurity, statistics

Tools

Ghidra

IDA Pro

Job description

Carnegie Mellon University’s CERT Division at CMU SEI seeks an Assistant AI Security Researcher to advance AI security research at national and global scale. You will co-author proposals, execute research, and present results to DoD sponsors, industry, and conferences.

Join a team focused on robustness, vulnerability discovery, and novel defenses for AI systems, with opportunities to publish, travel, and collaborate across academia, industry, and government.