AI Safety Red Teamer — Adversarial Testing & Robustness (Remote)

NEPSE Trading; Belgique; Remote; EUR 86,000 - 103,000; Full time

Job summary

Mercor is seeking an AI Safety Red Teamer to stress-test frontier AI models through adversarial prompts and vulnerability assessment. This remote contract role demands deep expertise in AI safety, red teaming, and written communication to report findings clearly.

Responsibilities include identifying jailbreaks and safety failures, evaluating model robustness across sensitive domains, and collaborating with researchers to improve alignment and safety benchmarks.

Qualifications

• Must have Bachelor's degree or higher in a related discipline.
• 5+ years of professional experience in AI Safety, AI Red Teaming, Trust & Safety, cybersecurity, investigative journalism, life sciences, or a related field.
• Strong analytical reasoning, prompt design, and written communication skills.
• Experience designing adversarial prompts or evaluating frontier AI systems.
• Preferred Experience with AI Red Teaming, RLHF, SFT, AI Alignment, or Trust & Safety.
• Familiarity with jailbreak testing, prompt engineering, or adversarial evaluation methodologies.
• Expertise in cyber, biosecurity, political content, misinformation, or scientific safety.

Responsibilities

• Design adversarial prompts to stress-test frontier AI models.
• Identify jailbreaks, unsafe behaviors, 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.

Skills

AI Safety

Red Teaming

Prompt design

Analytical reasoning

Written communication

Adversarial evaluation

Cybersecurity

Misinformation

Education

Bachelor's degree or higher

Job description

Mercor is seeking an AI Safety Red Teamer to stress-test frontier AI models through adversarial prompts and vulnerability assessment. This remote contract role demands deep expertise in AI safety, red teaming, and written communication to report findings clearly.

Responsibilities include identifying jailbreaks and safety failures, evaluating model robustness across sensitive domains, and collaborating with researchers to improve alignment and safety benchmarks.