AI Penetration Tester

@ Crossing Hurdles

About the Role

Crossing Hurdles, a recruitment firm, refers top candidates to world-leading AI research labs. This role is for an AI Penetration Tester responsible for red-teaming AI systems.

Key Responsibilities

• Red-team AI models by crafting jailbreaks and prompt injections.
• Generate high-quality human data by annotating failures and classifying vulnerabilities.
• Apply structured approaches using taxonomies, benchmarks, and playbooks.
• Document findings to produce reproducible reports and attack cases.
• Support multiple projects including LLM jailbreaks and socio-technical abuse testing.

Required Qualifications

• Prior red-teaming, cybersecurity or strong AI background for rapid learning.
• Expertise in adversarial machine learning, jailbreak datasets, prompt injection, RLHF/DPO attacks, and model extraction.
• Cybersecurity skills including penetration testing, exploit development and reverse engineering.
• Experience with socio-technical risk areas such as harassment, disinformation, or abuse analysis.
• Creative probing using psychology, acting or writing to develop unconventional adversarial methods.

Application Process

• Upload your resume.
• AI interview based on your resume (15 min).
• Submit a follow-up form.

Key skills/competency

• adversarial
• AI
• red-teaming
• cybersecurity
• penetration testing
• prompt injection
• RLHF
• socio-technical
• exploitation
• risk analysis