AI Red-Teamer

@ Crossing Hurdles

About AI Red-Teamer at Crossing Hurdles

Crossing Hurdles, a recruitment firm, refers top candidates to partners working with the world’s leading AI research labs to help build and train cutting-edge AI models. The position for AI Red-Teamer — Adversarial AI Testing (Advanced) is available on an hourly contract basis with flexible scheduling (full-time or part-time).

Key Responsibilities

• Red-team AI models and agents by crafting jailbreaks and exploit scenarios.
• Generate high-quality human data by annotating AI failures and classifying vulnerabilities.
• Apply structured approaches using taxonomies, benchmarks, and playbooks.
• Document findings comprehensively for reproducible reports and datasets.
• Support multiple projects including LLM jailbreaks and socio-technical abuse testing.

Required Qualifications

• Prior red-teaming experience in AI adversarial work, cybersecurity, or socio-technical probing OR a strong AI background.
• Expertise in adversarial machine learning including 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 innovate adversarial methods.

Application Process

(20 min process)

• Upload resume.
• AI interview based on your resume (15 min).
• Submit the provided form.

Key skills/competency

• Adversarial
• Cybersecurity
• Red-teaming
• Jailbreaks
• Prompt Injection
• Exploit Development
• Reverse Engineering
• Socio-technical
• Annotation
• Risk Analysis