Remote AI Red Teamer: Adversarial Security Testing

10a Labs; United States; Remote; USD 100,000 - 120,000; Full time

Benefits offered by this job

Salary: $100K-$120K

Performance-based annual bonus

Comprehensive health benefits

Remote work (U.S.-based)

Job summary

10a Labs, a safety and threat-intelligence leader in frontier AI, seeks an AI Red Teamer to test security and resilience of advanced AI systems and applications. You will design and execute red team assessments, craft adversarial inputs, and collaborate with engineers to improve defenses.

Ideal candidates have 2–5 years of experience, a CS/engineering/cybersecurity degree, and hands-on experience with tools like Burp Suite, Metasploit, Nmap, and Wireshark.

Qualifications

• Degree in Computer Science, Engineering, Cyber Security or related field, or equivalent practical experience.
• Strong understanding of cybersecurity principles and attack methodologies.
• Experience with security testing tools such as Splunk, Wireshark, Metasploit, Burp Suite, Nmap.
• Comfortable in Linux environments and scripting in Python or Bash.
• Excellent written and verbal communication skills.

Responsibilities

• Design and execute red team assessments against AI systems and infrastructure.
• Translate objectives into structured testing plans and attack strategies.
• Develop adversarial testing methodologies to evaluate safety and resilience.
• Craft prompts and attack chains to reveal unsafe system behavior.
• Identify vulnerabilities, risks, and failure modes through testing and analysis.
• Document findings and provide actionable risk-based recommendations.
• Collaborate with engineers and researchers to improve system security.
• Refine testing methodologies as new threats emerge.

Skills

Cybersecurity fundamentals

Adversarial thinking

Analytical skills

Problem-solving

Written and verbal communication

Education

Bachelor's degree in CS/Engineering/Cyber Security

Tools

Splunk

Wireshark

Metasploit

Burp Suite

Nmap

Job description

10a Labs, a safety and threat-intelligence leader in frontier AI, seeks an AI Red Teamer to test security and resilience of advanced AI systems and applications. You will design and execute red team assessments, craft adversarial inputs, and collaborate with engineers to improve defenses.

Ideal candidates have 2–5 years of experience, a CS/engineering/cybersecurity degree, and hands-on experience with tools like Burp Suite, Metasploit, Nmap, and Wireshark.