AI Red Team Tester — Adversarial Testing & Security Research

Orion Innovation; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Orion Innovation is seeking a high-caliber AI Red Team Tester to conduct adversarial testing of AI models, evaluate security tools, and drive remediation strategies. The role focuses on real-world deployment scenarios, bias detection, and safeguarding against harmful outputs while collaborating with global security teams and stakeholders.

The ideal candidate has at least five years in penetration testing or AI red teaming, a strong CS/IT background, and excellent communication skills to

Qualifications

• Minimum 5 years of penetration testing, red team operations, or AI Red Team experience.
• Background in AI red teaming or offensive cyber operations.
• Understanding of AI, machine learning, software applications, cloud computing, and networking.
• Excellent communication and stakeholder management skills.
• Ability to work effectively across geographies and time zones.

Responsibilities

• Design and execute adversarial testing campaigns against AI models and systems.
• Research attack vectors and prompt injection techniques to identify vulnerabilities and unintended behaviors.
• Evaluate and introduce AI security tools to reduce mean time to detect and respond to AI threats.
• Conduct red team exercises simulating real-world deployment scenarios and probe for biases and harmful outputs.
• Create adversarial datasets and benchmarks to evaluate model robustness.
• Collaborate with security teams to document findings, vulnerabilities, and remediation recommendations.
• Develop and maintain process documentation and reports on testing activities.

Skills

Penetration testing

Red team operations

AI Red Team experience

Communication skills

Stakeholder management

Education

Bachelor's degree in CS/IT/AI/Cybersecurity

Tools

SPLX

Garak

TextAttack

PyRIT

Burp Suite

Metasploit

Nessus

Cobalt Strike/Mythic/C2

NMAP

sqlmap

Job description

Orion Innovation is seeking a high-caliber AI Red Team Tester to conduct adversarial testing of AI models, evaluate security tools, and drive remediation strategies. The role focuses on real-world deployment scenarios, bias detection, and safeguarding against harmful outputs while collaborating with global security teams and stakeholders.

The ideal candidate has at least five years in penetration testing or AI red teaming, a strong CS/IT background, and excellent communication skills to