AI Security Professional | $80/hr Remote

Crossing Hurdles; United Kingdom; Remote; GBP 83,903; Part time

Job summary

A technology consulting firm seeks an AI Security Professional for remote, project-based work. You will engage in red-teaming exercises and adversarial testing, demanding strong expertise in cybersecurity and AI safety. The ideal candidate is adaptable with exceptional communication skills and can handle creative design of attack scenarios. This role offers $80/hour compensation, catering to a flexible commitment.

Qualifications

• Proven expertise in red-teaming, adversarial machine learning, cybersecurity, or related fields.
• Strong grasp of AI safety challenges and frontier model risks.
• Creative and systematic thinking in designing adversarial threat scenarios.

Responsibilities

• Collaborate with the Safety Team to design custom red-teaming exercises and training programs.
• Conduct adversarial testing across various domains to probe system robustness.
• Develop attack scenarios aligned with cutting-edge safety objectives.

Skills

red-teaming expertise

adversarial machine learning

cybersecurity knowledge

exceptional communication skills

Job description

AI Security Professional | $80/hr Remote

Position: Safety Team Research & Custom Projects Specialist

Type: Hourly Contract

Compensation: $80/hour

Location: Remote

Duration: Project-based, flexible

Commitment: Flexible, remote, project-driven

Role Responsibilities

• Collaborate with the Safety Team to design and execute custom red‑teaming exercises and targeted training programs
• Conduct adversarial testing across technical, social, and multimodal domains to probe system robustness
• Develop sophisticated attack scenarios and evaluation frameworks aligned with cutting‑edge safety objectives
• Document findings clearly, creating both technical reports and executive‑level summaries
• Contribute to ongoing AI risk, alignment, and adversarial resilience research efforts
• Support special projects, pilots, and rapid‑response evaluations as required

Requirements

• Proven expertise in red‑teaming, adversarial machine learning, cybersecurity, or related fields
• Strong grasp of AI safety challenges and frontier model risks
• Creative and systematic thinking in designing adversarial threat scenarios
• Exceptional communication skills for clear, structured reporting
• Adaptable and exploratory mindset comfortable with open‑ended, project‑based work

Preferred Qualifications

• Experience working with large language models (LLMs) or multimodal AI systems
• Knowledge of AI alignment, bias/fairness, misinformation, and security vulnerabilities
• Background combining technical exploits with social and psychological attack techniques
• Demonstrated ability to work independently on complex, ambiguous problems

Application process (Takes 20 min)

• Upload resume
• AI interview based on your resume (15 min)