Remote AI Security Consultant | Adversarial ML & Safety

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

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.