Remote AI Safety Red Teamer for Frontier Models

Mercor

Lisboa

Remote

EUR 87,000 - 104,000

Part time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Mercor is seeking an AI Safety Red Teamer for a remote contract role. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks, unsafe behaviors, hallucinations, and policy failures.

You will collaborate with AI researchers to improve alignment, robustness, and safety, document vulnerabilities, and contribute to red-teaming reports. A Bachelor’s degree and 5+ years of relevant experience are required.

Qualifications

  • Bachelor's degree or higher in Computer Science, Cybersecurity, Journalism, Communications, Psychology, Biology, Chemistry, Public Policy, or 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.

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

Analytical reasoning
Prompt design
Written communication
Adversarial prompts design
AI safety
AI systems
Jailbreak testing
Prompt engineering
Adversarial evaluation methods
Cybersecurity

Education

Bachelor's degree

Job description

Mercor is seeking an AI Safety Red Teamer for a remote contract role. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks, unsafe behaviors, hallucinations, and policy failures.

You will collaborate with AI researchers to improve alignment, robustness, and safety, document vulnerabilities, and contribute to red-teaming reports. A Bachelor’s degree and 5+ years of relevant experience are required.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Remote AI Safety Red Teamer for Frontier Models
Remote AI Safety Red Teamer for Frontier Models

Mercor • Almada

Remote
EUR 90,000 - 120,000
Remote Ai Safety Red Teamer For Frontier Models - Remote
Remote Ai Safety Red Teamer For Frontier Models - Remote

Mercor • Almada

Remote
EUR 90,000 - 120,000
Remote AI Safety Red Teamer — Stress-Test Frontier Models
Remote AI Safety Red Teamer — Stress-Test Frontier Models

Mercor • Lisboa

Remote
EUR 86,000 - 103,000
AI Safety Red Team Specialist (Remote Contract)
AI Safety Red Team Specialist (Remote Contract)

Mercor • Viseu

Remote
EUR 88,000 - 105,000
Remote AI Safety Red Teamer - Stress-Test Frontier Models
Remote AI Safety Red Teamer - Stress-Test Frontier Models

Mercor • Lisboa

Remote
EUR 83,000 - 100,000
Frontier AI Safety Red Team Expert
Frontier AI Safety Red Team Expert

Mercor • Viseu

On-site
EUR 70,000 - 100,000
Ai Safety Specialist - Remote | Upto $84/Hr
Ai Safety Specialist - Remote | Upto $84/Hr

Mercor • Lisboa

Remote
EUR 86,000 - 103,000
Ai Safety Red Teamer Expert
Ai Safety Red Teamer Expert

Mercor • Viseu

On-site
EUR 70,000 - 100,000
Ai Safety Specialist - Fully Remote | Upto $70/Hr - Remote
Ai Safety Specialist - Fully Remote | Upto $70/Hr - Remote

Mercor • Viseu

Remote
EUR 88,000 - 105,000
Ai Safety Specialist - Fully Remote | Upto $84/Hr
Ai Safety Specialist - Fully Remote | Upto $84/Hr

Mercor • Lisboa

Remote
EUR 87,000 - 104,000
Top locations