AI Security Researcher

About the AI Security Researcher Role

Crossing Hurdles, a recruitment firm, is referring top candidates to world-leading AI research labs. In this role as an AI Security Researcher, you will red-team AI models and agents by crafting jailbreaks, prompt injections, misuse cases, and exploit scenarios.

Key Responsibilities

• Red-team AI models: develop jailbreaks and injection tests.
• Generate high-quality human data and annotate AI failures.
• Apply taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document findings with reproducible reports and datasets.
• Support multiple projects including LLM jailbreaks and socio-technical abuse testing.

Required Qualifications

• Prior red-teaming or cybersecurity experience, or strong AI background.
• Expertise in adversarial machine learning including RLHF/DPO attacks.
• Cybersecurity skills: penetration testing, exploit development, reverse engineering.
• Experience with socio-technical risks such as harassment and disinformation analysis.
• Creative probing skills using psychology, acting, or writing.

Application Process

• Upload your resume.
• Participate in an AI interview based on your resume (15 min).
• Submit the application form.

Key Skills/Competency

Adversarial Testing, Cybersecurity, AI, Red-Teaming, Penetration Testing, Exploit Development, Reverse Engineering, Annotation, LLM, Socio-technical Analysis