Join the Threat Analysis Directorate at CERT Division as an AI Security Researcher and contribute to pioneering research in AI security. You will collaborate with elite professionals to develop cutting-edge methodologies for analyzing AI system robustness, reverse engineer malicious code, and evaluate defense mechanisms against sophisticated threats. Utilizing tools like Numpy, Pytorch, Tensorflow, ART, NSA Ghidra, and IDA Pro, you’ll conduct vulnerability assessments, advise on security topics, and publish findings at academic conferences. Ideal candidates hold a BS with 10 years of experience or an MS/PhD in related fields, demonstrating expertise in AI/ML and cybersecurity, along with strong communication skills and a passion for intellectual curiosity. This role offers the opportunity to influence national AI security strategy while working on impactful projects that address emerging threats at a global scale.
Skills
Python
Pytorch
Tensorflow
Numpy
C
C++
Ghidra
IDA Pro
AI/ML
Cybersecurity
CI/CD
Reverse Engineering
Vulnerability Assessment
Security Research
Tool Development
Framework Development
Methodology Evaluation
Technical Communication
Low-Level Programming
What you'll do
Develop advanced methods to analyze AI system robustness.
Identify and assess vulnerabilities in AI systems for attackers.
Reverse engineer malicious code to support high-impact customers.
Evaluate effectiveness of AI security tools and techniques.
Influence AI security research community through thought leadership.
Publish findings on threats and vulnerabilities in AI systems.
Apply AI to enhance existing cybersecurity research methodologies.
What we're looking for
BS in ML, cybersecurity, statistics, or related field with 10 years of experience; MS with 8 years; PhD with 5 years.
Deep interest and practical experience in AI/ML and cybersecurity vulnerability research and analysis.
Familiarity with implementing AI/ML techniques and common software packages like Numpy, Pytorch, Tensorflow.
Experience with reverse engineering tools (NSA Ghidra, IDA Pro) and low-level programming languages.
Ability to develop frameworks and methodologies for evaluating the effectiveness of technologies.
Market check
Salary context
This listing doesn't show a salary. Similar roles on FindRole typically pay
$173,000–$260,000.
Peer median band
$173,000–$260,000
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$166,670–$246,150
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
Employer
About Carnegie Mellon University
Carnegie Mellon University is a leading private research university in Pittsburgh, Pennsylvania, internationally recognized for programs in computer science, engineering, business, the arts, and artificial intelligence. Industry: Higher Education & Research
Carnegie Mellon University currently has
36 open roles
on FindRole.