Project Overview:

Join a growing community of professionals advancing the next wave of AI. As an AI Trainer, you’ll play a hands-on role by analyzing and providing feedback on data to improve LLM performance, helping ensure that the next generation of AI technology is accurate and trustworthy.

We are seeking a skilled Cybersecurity & AI Red-Teaming Expert to work as a project consultant in our AI Labor Marketplace. This is not a full-time employment position — you will be engaged as an expert project consultant on a contract basis.

Location: U.S.-based experts only

Engagement: Part-time, project-based expert evaluation work

Work Type: Remote

Project Summary:

Support AI red-teaming and evaluation efforts by identifying vulnerabilities, testing model robustness, developing adversarial scenarios, and documenting observed behaviors. Contributors will help evaluate frontier AI systems through structured cybersecurity, safety, and reasoning-focused assessments.

Consultant Engagement Terms:

This is a project-based consultant role. Consultants will be paid on a per-project basis; hourly rates are estimates based on anticipated completion time. Consultants control their own schedule, provide their own tools, and may simultaneously provide services to other vendors or employers (subject to those vendors’ allowances).

Responsibilities:

Contributors will:

• Conduct AI red-teaming, jailbreak, and prompt-injection testing
• Develop adversarial prompts and attack methodologies
• Evaluate model responses for robustness, safety, and compliance
• Identify and document vulnerabilities, weaknesses, and failure modes
• Produce written rationales and structured analysis reports
• Participate in multi-turn testing workflows against AI systems
• Apply cybersecurity and threat-modeling expertise to AI evaluation tasks
• Collaborate with project teams through documented findings and recommendations

Expected Outcomes:

• High-quality adversarial test cases
• Well-documented vulnerability reports
• Structured evaluation judgments
• Clear written justifications for findings
• Consistent adherence to project guidelines and evaluation frameworks
• Reliable completion of assigned project work within agreed schedules

Qualifications:

• Professional experience in cybersecurity, AI, or related analytical disciplines
• Strong adversarial thinking and problem-solving skills
• Experience in one or more of the following:
• AI red-teaming
• Offensive security
• Penetration testing
• Bug bounty research
• CTF participation
• Threat intelligence
• AppSec
• Vulnerability research
• AI safety
• LLM evaluation
• ML/NLP engineering
• Excellent written communication and documentation skills
• U.S.-based and eligible to work as an independent contractor
• Availability of 20+ hours per week preferred
• Ability to begin work immediately or on short notice preferred

LinkedIn Data Security and Privacy Notice:

https://legal.linkedin.com/content/dam/legal/Global-Data-Privacy-Notice_LI_TalentCommunity.pdf