Get more replies from employers
Send a job-specific resume in minutes.
Carnegie Mellon University in the United States seeks an experienced AI Red Team Engineer to emulate adversaries against AI-enabled platforms. You will contribute to national security objectives by developing TTPs, scripting tools in Python, PowerShell, C, and BASH, and collaborating with CERT teams and partners.
Strong background in offensive cyber and AI security is required. Ideal candidates are seasoned professionals with penetration testing or red-teaming experience, capable of traversing
SEI conducts research and development in software engineering,systems engineering, cybersecurity, and many other areas ofcomputing, working to introduce private-sector innovations intogovernment. The SEI works closely with defense and governmentorganizations, industry, and academia to continually improvesoftware-intensive systems. Its core purposes are to helporganizations improve software engineering capabilities, advancecybersecurity methods and technologies, and bring the discipline ofsoftware engineering to AI systems.
The CERT Threat Analysis (TA) Directorate conducts research anddevelopment activities to identify, analyze, coordinate disclosure,and mitigate threats and vulnerabilities in systems and software.The TA Directorate is currently comprised of three teams:Artificial Intelligence ( AI) Security, Malware and VulnerabilityExploitation, and Platform and Mission Engineering . The AISecurity team works on advancing the state of the art in AIsecurity at a national and global scale. The Malware andVulnerability Exploitation (MVE) team works to improvecyber-tradecraft analysis within strategic target communities tocounter adversarial use of the Internet and related technologies .The v ulnerability side of MVE (home of the CERT CoordinationCenter) works with an expansive network of vendors, partners, andcollaborators to reduce the societal harm of vulnerable softwareand systems . The Platform and Mission Engineering team developsand maintains tools, environments, and operational support for themalware analysis, reverse engineering, vulnerability analysis, andAI security domains .
As an AI Red Team Engineer on the AI Security team, you will play acentral role in adversary emulation exercises and capabilitydevelopment for our mission partners. Due to our unique positionwithin the TA Directorate, the systems we red- team fall outsidethe realm of 'traditional' enterprise red teaming. Our targets arecommonly AI-enabled platforms used within national securitycontexts.
But this isn't a \"make the LLM say the bad thing\" type of AI redteam. We operate across multiple domains, meaning that our redteamers are expected to be experts in offensive cyber in additionto AI security. If you are experienced with offensive cybertradecraft and have an interest in breaking into AI, this could bea good fit. Most of our red teamers are actively takinggraduate-level technical courses at CMU and/or pursuing technicalcertifications. Perpetual learning is a core part of what wedo.
While our red team exists within a research organization, researchis only a portion of the work performed by our red team. Much ofthe work will involve red teaming real-world systems, sometimes atan aggressive cadence. This can involve planning and rehearsing redteam TTPs, traveling to field sites, and presenting relevantfindings. Like most red teams, we don't get to pick and choose ourtargets. This means that our red team needs to be well-rounded(both as individuals and as a team). Thus, we expect all applicantsto be savvy with both Windows and Linux, solid with TCP/IP, andhave some experience with penetration testing and/or redteaming.
Arlington, VA, Pittsburgh, PA
Software/Applications Development/Engineering
Staff – Regular
Full time
Salary More Information: