AI Safety Red Teamer
Stress-test Mercor partner labs’ frontier AI systems by probing for vulnerabilities in high-risk domains. Contribute findings to safety benchmarks and help researchers improve model robustness and alignment.
विवरण
- Create adversarial prompts to test frontier AI models.
- Find jailbreaks, unsafe behavior, hallucinations, and policy failures.
- Assess model robustness in sensitive areas such as misinformation, cybersecurity, biosecurity, fraud, and political content.
- Record vulnerabilities and contribute to safety benchmarks and red-team reports.
- Work with AI researchers to strengthen model alignment, robustness, and safety.
- Support projects that train and improve AI systems.
- Set your own schedule; project length may change or end early based on business needs and performance.
आवश्यकताएँ
- Bachelor’s degree or higher in computer science, cybersecurity, journalism, communications, psychology, biology, chemistry, public policy, or a related field.
- At least five years of professional experience in AI safety, AI red teaming, trust and safety, cybersecurity, investigative journalism, life sciences, or a related area.
- Strong analytical reasoning, prompt design, and writing skills.
- Experience creating adversarial prompts or evaluating frontier AI systems.
- Preferred: experience with AI red teaming, RLHF, SFT, AI alignment, or trust and safety.
- Preferred: familiarity with jailbreak testing, prompt engineering, or adversarial evaluation methods.
- Preferred: expertise in one or more sensitive areas, including cybersecurity, biosecurity, political content, misinformation, or scientific safety.
- Engagement is as an independent contractor.
- Must be able to work without H-1B or STEM OPT support.
लाभ
- Fully remote work with a flexible schedule.
- Weekly payments through Stripe or Wise for services rendered.
- Work alongside leading AI researchers and safety teams.
- Help shape how AI systems respond to complex, real-world safety challenges.
- Competitive pay.
- Reasonable accommodations available upon request.
- Referral payments of up to $340 for each successful referral, subject to limits.