Remote AI Red Team - Safety & Adversarial Testing

Mercor; San Francisco (CA); On-site; USD 100,000 - 140,000; Full time

Job summary

Obsidian is seeking a remote AI red team expert responsible for probing AI models with adversarial inputs to uncover vulnerabilities. You will apply structured testing frameworks, document findings, and generate high-quality data to improve AI safety.

The ideal candidate brings red-teaming experience, a curious mindset, and clear communication skills to explain risks effectively. Join us to play a pivotal role in enhancing the robustness of AI systems.

Qualifications

• Prior experience in AI adversarial work including cybersecurity.
• Strong communication skills for explaining risks to stakeholders.
• Ability to structure tests using frameworks.

Responsibilities

• Red team conversational AI models and agents.
• Generate high‑quality human data through annotation and flagging.
• Document reproducibly to produce actionable reports and datasets.

Skills

Red‑teaming experience (AI adversarial work)

Curiosity and adversarial mindset

Structured approach to testing

Clear communication skills

Adaptability across projects

Job description

Obsidian is seeking a remote AI red team expert responsible for probing AI models with adversarial inputs to uncover vulnerabilities. You will apply structured testing frameworks, document findings, and generate high-quality data to improve AI safety.

The ideal candidate brings red-teaming experience, a curious mindset, and clear communication skills to explain risks effectively. Join us to play a pivotal role in enhancing the robustness of AI systems.