AI Safety Red Teamer - United States Remote Contract
Mercor is seeking a contract AI Safety Red Teamer to challenge frontier AI models and uncover vulnerabilities. The role focuses on high-risk domains and supports the development of safer, more reliable AI systems.
Aprašymas
- Create adversarial prompts that rigorously challenge frontier AI models
- Detect jailbreaks, unsafe behavior, hallucinations, and failures to follow safety policies
- Assess model resilience across misinformation, cybersecurity, biosecurity, fraud, political content, and other sensitive areas
- Record discovered weaknesses and support safety benchmarks and red-teaming reports
- Work with AI researchers to advance model alignment, robustness, and safety
- Help protect and improve emerging frontier AI systems
- Shape how AI models handle difficult safety scenarios in real-world contexts
Reikalavimai
- 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 judgment, prompt-development ability, and written communication skills
- Hands-on experience creating adversarial prompts or assessing frontier AI systems
- Preferred: background in AI red teaming, RLHF, SFT, AI alignment, or trust and safety
- Preferred: familiarity with jailbreak assessments, prompt engineering, or adversarial evaluation methods
- Preferred: expertise in nuanced areas such as cybersecurity, biosecurity, political content, misinformation, or scientific safety
- Availability to work as an independent contractor
- H-1B and STEM OPT candidates are not supported
Privalumai
- Work fully remotely
- Set your own working hours and complete assignments on a flexible schedule
- Receive weekly payments through Stripe or Wise
- Project duration may change or end early based on business needs and performance
- Competitive compensation
- Work alongside leading AI researchers and safety teams
- Reasonable accommodations are available upon request
- Referral program offering up to $340 for each successful referral, subject to referral limits