AI Red Teamer, Cybersecurity (Remote)

📋 Description

• Design technically grounded adversarial prompts that test whether models provide meaningful
• Evaluate model-generated code and technical output for functional correctness, determining whether
• Test model behavior across offensive categories, including malware generation, vulnerability
• Probe dual-use boundaries by testing how models respond to queries that combine legitimate security
• Simulate attacker personas at varying skill levels, including opportunistic, intermediate, and
• Test multi-step and multi-turn attack chains, including scenarios in which early turns establish

🎯 Requirements

• Professional experience in offensive security, penetration testing, red teaming, vulnerability
• Ability to read, write, and evaluate code in languages commonly used for offensive tooling, such as
• Understanding of common attack frameworks, techniques, and procedures, including MITRE ATT&CK
• Ability to assess the functional correctness and real-world exploitability of model-generated
• Strong hands-on experience using multiple LLMs, such as ChatGPT, Claude, Gemini, or open-source
• Creative and adversarial problem-solving skills