Remote AI Security Red Teamer (Contract)

Bezel; United States; Remote; USD 96,000 - 165,000; Part time

Job summary

Parallel is seeking an AI Security Red Teamer for remote contract work in the United States. You will design and execute authorized adversarial tests against generative AI models, identify vulnerabilities, and document actionable findings to strengthen defenses.

The role requires five-plus years of web pentesting experience, strong AI vulnerability analysis skills, and the ability to complete Parallel’s practical CTF assessment.

Qualifications

• 5+ years of web penetration testing experience.
• Demonstrated experience identifying and analyzing AI vulnerabilities.
• Strong understanding of generative AI models and their architectures.
• Ability to pass Parallel’s practical CTF assessment.
• Ability to work remotely and communicate with a remote team.

Responsibilities

• Design and execute authorized adversarial tests against generative AI models, agents, applications, and infrastructure.
• Investigate prompt injection, jailbreaks, unintended tool use, data exposure, and other AI vulnerabilities.
• Apply web penetration testing techniques to AI-related applications and services.
• Build reproducible attack scenarios and evaluation cases for model training and security testing.
• Assess impact of findings and recommend practical mitigations.
• Collaborate with project teams to validate weaknesses and retest improvements.
• Document methods, evidence, and results for reproducibility.

Skills

Web penetration testing

AI vulnerabilities analysis

Generative AI understanding

Written communication

CTF assessment

Remote collaboration

Education

Computer science or related field

Tools

Python

Node.js

CTF tooling

Job description

Parallel is seeking an AI Security Red Teamer for remote contract work in the United States. You will design and execute authorized adversarial tests against generative AI models, identify vulnerabilities, and document actionable findings to strengthen defenses.

The role requires five-plus years of web pentesting experience, strong AI vulnerability analysis skills, and the ability to complete Parallel’s practical CTF assessment.