AI Red-Teamer - Adversarial AI Testing

About the Role

The AI Red-Teamer - Adversarial AI Testing role involves red-teaming AI models and agents by crafting jailbreaks, prompt injections, misuse cases, and exploit scenarios. This position supports multiple projects including LLM jailbreaks and socio-technical abuse testing across various customers.

Key Responsibilities

• Red-team AI models using creative adversarial techniques.
• Generate high-quality human data by annotating AI failures.
• Apply structured approaches with taxonomies, benchmarks, and playbooks.
• Document findings to produce reproducible reports and datasets.
• Support multiple projects including LLM jailbreaks and socio-technical abuse testing.

Qualifications

• Prior red-teaming experience in AI adversarial work or cybersecurity OR strong AI background.
• Expertise in adversarial machine learning (e.g., jailbreak datasets, prompt injection, RLHF/DPO attacks, 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 skills using psychology, acting, or writing.

Application Process

The process takes approximately 35 minutes, including resume upload, a 15-minute AI interview, and form submission.

Key skills/competency

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