Security Consultant (AI) | $90/hr Remote

Crossing Hurdles; United States; Remote; USD 69,000 - 124,000; Part time

Job summary

Crossing Hurdles is seeking a Security Consultant (AI) for remote, contract work. The role focuses on adversarial machine learning, red teaming for language models, and evaluating AI safety risks across real-world scenarios.

The consultant will design rigorous evaluation methods, create regression test suites, and collaborate with stakeholders to translate findings into concrete improvements. Strong communication and credible security research background are required.

Qualifications

• Advanced degree or equivalent practical background in CS, cybersecurity or ML.
• Proven experience researching, testing or uncovering vulnerabilities in AI safety and jailbreak contexts.
• Knowledge of LLM architectures and prompt engineering is desirable.

Responsibilities

• Design and implement evaluation methods for AI safety and jailbreak scenarios.
• Create cross-domain strategies to uncover multi-turn adversarial bypass patterns.
• Develop regression test suites for jailbreaks and prompt-injection vulnerabilities.
• Build evaluation frameworks that stress-test AI models against real threats.
• Collaborate with stakeholders to translate findings into actionable model improvements.
• Document methodologies and findings in clear reports and presentations.

Skills

Adversarial ML

LLM red teaming

AI safety evaluation

Strong written/verbal comms

Education

PhD or MS in CS/Cybersecurity/ML or equivalent

Tools

Security assessment tools

Job description

Position: Security Consultant (AI) | $90/hr Remote

Type: Contract

Compensation: $50 - $90/hour

Location: Remote

Commitment: 10-40 hrs/week

Role Responsibilities

• Design and implement advanced methodologies for evaluating AI system safety, focusing on ethical jailbreaks, LLM red teaming, prompt injection, and tool-use abuse scenarios.
• Create comprehensive cross-domain elicitation strategies to uncover multi-turn and complex adversarial bypass patterns in AI models.
• Develop, maintain, and update regression test suites that systematically test for jailbreak susceptibility and prompt-injection vulnerabilities.
• Construct robust evaluation frameworks that stress-test AI models against real-world adversarial threats, aiming to enhance overall system robustness.
• Collaborate with technical stakeholders to translate security findings into actionable improvements for model safety and risk mitigation.
• Document methodologies, findings, and best practices in clear, well-structured written reports and presentations for both technical and non-technical audiences.

Requirements

• Have strong relevant experience in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security domain.
• Proven experience researching, testing, or uncovering vulnerabilities related to ethical jailbreaks, prompt injection, tool-use abuse, or adversarial AI attacks.
• Advanced degree (PhD, MS) in computer science, cybersecurity, machine learning, or a relevant discipline, or equivalent operational/professional background.
• High credibility and recognition within the AI security or adversarial ML community such as published research, open-source tools, or conference presentations.
• Exceptional written and verbal communication skills, with a strong focus on clear documentation and collaborative problem-solving.
• Familiarity with current LLM architectures, prompt engineering techniques, and security assessment tools is highly desirable.