Frontier AI Safety Red Team Specialist

Obsidian; Brussel Hoofdstad; À distance; EUR 90 000 - 130 000; Plein temps

Résumé du poste

Obsidian in Belgium seeks experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing.

You will design challenging prompts, uncover jailbreaks, unsafe behaviours, and policy failures, and document findings for safety benchmarking and red-teaming reports.

Collaborate with researchers to improve alignment, robustness, and safety across high-risk domains.

Qualifications

• Bachelor's degree or higher in a relevant field as listed.
• 5+ years of professional experience in AI Safety, Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or related field.
• Strong analytical reasoning, prompt design, and written communication skills.
• Experience designing adversarial prompts or evaluating frontier AI systems.

Responsabilités

• 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.

Connaissances

Prompt design

Analytical reasoning

Written communication

Red teaming

Formation

Bachelor's degree or higher (CS/Cybersecurity/Journ/Comm/Psych/Bio/Chem/Public Policy or related)

Outils

Jailbreak testing

Adversarial evaluation

Prompt engineering

Description du poste

Obsidian in Belgium seeks experienced AI Safety Red Teamers to identify vulnerabilities in frontier AI systems through adversarial testing.

You will design challenging prompts, uncover jailbreaks, unsafe behaviours, and policy failures, and document findings for safety benchmarking and red-teaming reports.

Collaborate with researchers to improve alignment, robustness, and safety across high-risk domains.