Frontier AI Safety Red Teamer

Obsidian; Madrid; A distancia; EUR 90.000 - 130.000; Jornada completa

Descripción de la vacante

Obsidian is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high‑risk topics with rigorous analysis and clear reporting.

Responsibilities include stress‑testing models, documenting vulnerabilities, and collaborating with researchers to improve alignment, robustness, and safety.

Formación

• Requires a degree and 5+ years in AI safety, red teaming, or related fields.
• Strong analytical reasoning and clear written communication are essential.
• Experience designing adversarial prompts or evaluating frontier AI systems is preferred.

Responsabilidades

• Design adversarial prompts to stress-test frontier AI models.
• Identify jailbreaks, unsafe behaviours, hallucinations, and policy failures.
• Evaluate model robustness across misinformation, cyber, biosecurity, fraud, political content, and other sensitive domains.
• Document vulnerabilities and contribute to safety benchmarking and red-teaming reports.
• Collaborate with AI researchers to improve model alignment, robustness, and safety.

Conocimientos

Prompt design

Analytical reasoning

Written communication

Adversarial testing

Educación

Bachelor's degree or higher (CS/related)

Descripción del empleo

Obsidian is seeking experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing. You will design challenging prompts, uncover model weaknesses, and evaluate AI behavior across high‑risk topics with rigorous analysis and clear reporting.

Responsibilities include stress‑testing models, documenting vulnerabilities, and collaborating with researchers to improve alignment, robustness, and safety.