Senior Adaptive Threat Simulation Red Teamer
Core
Conducts research, analysis, and testing of computer/network vulnerabilities via vulnerability assessments, penetration testing, red team operations, and social engineering, with a specific focus on AI/LLM security risks and adversarial attack techniques.
Role type
Senior IC security researcher (AI/LLM red teaming)
Builds
Security assessments and risk reports for financial lines of business
Domain
Cybersecurity / AI Security / Offensive Security
Deliverable
production ML models
Required skills
Red teaming, penetration testing, AI/LLM security concepts, adversarial attack techniques, implant development, network analysis, MITRE ATT&CK, threat actor emulation, scripting (Python, C#, PowerShell, C)
Preferred skills
Financial industry experience, FOSS security assessment, OSCP/GPEN/OSCE certifications
Technologies
Metasploit, Burp Suite, Cobalt Strike, Active Directory, Python, C#, PowerShell, C
Responsibilities
Lead AI security testing engagements and define safe testing guardrails; execute covert red team operations emulating advanced threat actors; identify attack paths and control weaknesses in AI-enabled systems; document risk and business impact of findings; assist Lines of Business with vulnerability remediation.
Seniority
Senior, hands-on IC
