AI Red Team Tester

About the Role: AI Red Team Tester

Our client, a prestigious global firm, is seeking an experienced hands-on AI Red Team Tester for a long-term contract. This remote position requires a credentialed security professional located in the US and involves a 40-hour work week. The Global Red Team Tester will be pivotal in identifying vulnerabilities in AI models, developing new evaluation frameworks, and enhancing the firm's security posture against emerging AI threats.

Key Responsibilities:

• Conduct red team exercises simulating real-world deployment scenarios and edge cases.
• Systematically probe for bias, toxicity, misinformation generation, and other harmful outputs across diverse contexts and demographics.
• Improve the firm's security posture against emerging AI threats, focusing on executing standardized security tests.
• Design and execute comprehensive adversarial testing campaigns against AI models, including large language models, multimodal systems, and autonomous agents.
• Research attack vectors and prompt injection techniques to identify model vulnerabilities, jailbreaks, and unintended behaviors.
• Evaluate and introduce AI Security tools that decrease mean time to detect and respond to AI-specific threats.
• Create adversarial datasets and benchmarks to evaluate model robustness under various attack conditions.
• Collaborate with security teams (e.g., GSOC, member firm security teams, developers) to perform red teaming activities.
• Document and present findings, vulnerabilities, and remediation recommendations to drive the mitigation of identified risks.
• Develop and maintain process documentation, create reports on testing activities, track operational metrics, and perform other programmatic tasks to support the AI Red Team's function.

Skills and Experience Desired:

• Minimum 5 years of penetration testing or red team operations experience.
• Background in AI red teaming, web application penetration testing, application/network penetration testing, red team operations, or cybersecurity.
• Familiarity with threat intelligence.
• Understanding of Artificial Intelligence, Machine Learning, software applications, cloud computing, and networking.
• Excellent communication and stakeholder management skills.
• Ability to work effectively across geographies and time zones.

Core Technical Skills Include:

• Testing tools: SPLX, Garak, TextAttack, PyRIT, Burp Suite, Metasploit, Nessus, Cobalt Strike/Mythic/C2, NMAP, sqlmap, or similar tools.
• Web application technologies: Layer 7 protocols (HTTP, DNS, FTP).
• Technical experience: Generative AI, Agents, A2A, and/or MCP.
• Programming languages: Python, Ruby, Go, PowerShell, bash or similar.
• Education: Computer science, information technology, or cybersecurity degree (Bachelor's or higher preferred) or equivalent work experience.
• Certifications: OSCP, GPEN, GPXN, AI Red Teamer Job Role Path (HackTheBox), AISEC+, or other industry AI or Red Team related certifications desired.

Key skills/competency

• AI Red Teaming
• Penetration Testing
• Vulnerability Assessment
• Adversarial AI
• Prompt Injection
• Large Language Models
• Cybersecurity
• Python
• Threat Intelligence
• Security Operations