Summary
We are seeking an AI Security Engineer – Red Team to join a highly technical team performing advanced security assessments of AI-enabled systems and the environments supporting them.
This position goes well beyond testing AI models alone. The role requires a strong foundation in offensive cybersecurity, penetration testing, networking, operating systems, and software security, along with an interest in applying those skills to emerging AI technologies. You’ll work hands-on with complex, real-world systems, identify weaknesses across multiple layers of the technology stack, develop attack methods and tooling, and help teams better understand and defend against evolving security threats.
Responsibilities:
- Plan and execute penetration tests, red team exercises, and adversarial security assessments
- Evaluate AI-enabled technologies across applications, operating systems, networks, infrastructure, and other supporting components
- Identify and demonstrate vulnerabilities and potential attack paths within complex technical environments
- Build scripts and offensive security tools using Python, C, BASH, and PowerShell
- Analyze network communications, system behavior, software, and source code as part of security assessments
- Apply reverse engineering and exploit-development techniques where appropriate
- Research and develop new approaches for testing emerging technologies and security controls
- Document findings and translate highly technical issues into clear risks and recommendations
- Collaborate with technical teams and share knowledge, tools, and security practices with others
Qualifications:
- Hands-on professional experience in red teaming, penetration testing, offensive security, or exploit development
- Strong working knowledge of Windows and Linux security
- Deep understanding of TCP/IP, network protocols, and network analysis, including experience with tools such as Wireshark
- Proficiency with Python, C, and BASH; PowerShell experience or willingness to develop proficiency
- Experience using offensive security and command-and-control platforms such as Cobalt Strike, Sliver, or comparable tools
- Familiarity with reverse engineering and binary analysis using tools such as Ghidra, IDA Pro, or similar
- Ability to review code and identify common software vulnerabilities
- Bachelor’s degree in a technical field and 5+ years of relevant cybersecurity experience, or an equivalent combination of education and experience
- Strong written and verbal communication skills, including the ability to communicate technical findings to non-specialists
- Ability to meet applicable background investigation and U.S. government security clearance requirements
Preferred:
- Experience evaluating the security of AI/ML technologies or AI-enabled systems
- Offensive security certifications such as OSCP, CPTS, CCNA, CWEE, GCPN, GAWN, GXPN, CRTO, CRTL, OSEP, OSWE, FORGE/RIOT, or demonstrated work experience
- Ongoing professional development through advanced technical training, certifications, coursework, or independent research
- Experience mentoring or providing technical guidance to other security professionals