Associate AI Red Team Engineer

Who We Are

SEI conducts research and development in software engineering, systems engineering, cybersecurity, and many other areas of computing, working to introduce private-sector innovations into government.The SEI works closely with defense and government organizations, industry, and academia to continually improve software-intensive systems. Its core purposes are to help organizations improve software engineering capabilities, advance cybersecurity methods and technologies, and bring the discipline of software engineering to AI systems.

What We Do

The CERT Threat Analysis (TA) Directorate conducts research and development activities toidentify, analyze, coordinate disclosure, and mitigatethreats andvulnerabilities in systems and software. The TA Directorate is currentlycomprisedofthreeteams: Artificial Intelligence (AI)Security,MalwareandVulnerabilityExploitation, andPlatform and Mission Engineering. The AI Security team workson advancing the state of the art in AI security at a national and global scale.The Malwareand Vulnerability Exploitation (MVE)team works to improve cyber-tradecraft analysis within strategic target communities to counter adversarial use of the Internet and related technologies. Thevulnerabilityside of MVE(home of the CERT Coordination Center) works with an expansive network of vendors, partners, and collaborators to reduce the societal harm of vulnerable software and systems.ThePlatform and Mission Engineering teamdevelops andmaintainstools,environments, and operational support forthemalware analysis, reverse engineering, vulnerability analysis, and AI securitydomains.

Position Summary

As an AI Red Team Engineer on the AI Security team, you will playa central rolein adversary emulation exercises and capability development for our mission partners. Due to our unique position within the TA Directorate, the systems wered-teamfall outside the realm of 'traditional' enterprise red teaming. Our targets are commonly AI-enabled platforms used within national security contexts.
 

But thisisn'ta "make the LLM say the bad thing" type of AI red team. Weoperateacross multiple domains, meaning that our red teamers are expected to be experts in offensive cyber in addition to AI security. If you are experienced with offensive cyber tradecraft and have an interest in breaking into AI, this could be a good fit. Most of our red teamers are actively taking graduate-level technical courses at CMU and/or pursuing technical certifications. Perpetual learning is a core part of what we do.

While our red team exists within a research organization, research is only aportionof the work performed by our red team. Much of the work will involve red teaming real-world systems, sometimes at an aggressive cadence. This can involve planning and rehearsing red team TTPs, traveling to field sites, and presenting relevant findings. Like most red teams, wedon'tget topick and chooseour targets. This means that our red team needs to be well-rounded (both as individuals and as a team). Thus, we expect all applicants to be savvy with both Windows and Linux, solid with TCP/IP, and have some experience with penetration testing and/or red teaming (CTF experience may be relevant for Assistant and Associate levels).
 

Whatyou’lldo:

• Red team real-world AI-enabled systems(both the model and the hardware/software/network that it runs on) in support of national securityobjectives.

• Develop new tactics, techniques, and procedures for attacking AI-enabled systemsand related softwarein order tobetter prepare defenders for real-world threats. 

• Write tools in Python, PowerShell, C, and BASH to enable red team operations.

• Represent the CERT technical portfolio of work and operations; communicate with external mission partners andinternalcollaboratorsin concert with CERT directorates and teams. 

Who you are:

• Bachelor's Degree in Computer Scienceor a relevant technical discipline with three (3) years of relevant work experience; or a MS in Computer Science or a relevant technical discipline with one (1) year of relevant work experience; or a PhD in Computer Science or other relevant technical discipline.Other educational backgrounds of a technical nature with experience as described may be considered.

• You havepreviouspenetration testing, red teaming, or exploit development experience. 

• You haveprevioushands-on experience with at least one command and control framework (e.g., Cobalt Strike, Sliver).

• You have experience programming/scripting in Python, C, and BASH(without theassistanceof AI)andare willing to learn PowerShell. 

• You haveexperiencewith reverse engineering tools (e.g.NSAGhidra, IDA Pro).

• Youare able toread code and quickly spot basic vulnerabilities without theassistanceof AI or fuzzing.

• You arevery familiarwith TCP/IP and all layers of the OSI model.You have experienceusing Wireshark and can explainhow common network protocols work.

• You have experience in assessing the security of both Linux and Windows systems. Experience with mobile(e.g., Android)and other operations systems is also appreciated.

• You have at leastoneof the following relevant certifications:OSCP, CPTS, FORGE/RIOT,eJPT, CBBH, BSCP, PNPT, GRTP, GPEN.Applicants without these certifications will still be considered if equivalent experience is clearlydemonstratedduring technical interviews.

• You have excellent communication skills (oral and written), particularlyregardingtechnical communications with non-experts.  

• You enjoy mentoring and cross-training others and sharing knowledge within the broader community. 

• You have a willingness to travel (25%) outside of your office location to other SEI offices, sponsor sites, conferences, and offsite meetings. 

• You will be subject to a background investigation, and you must have the ability to obtain andmaintaina Department ofWarsecurity clearance.