51 – 200 Angajați
Informațiile disponibile despre Mercor nu includ suficiente date verificate despre produsele, serviciile, clienții, sectorul sau direcția de recrutare a companiei pentru a permite o prezentare exactă. Sunt necesare mai multe surse înainte de a descrie activitatea companiei sau oportunitățile oferite.
AI Model Safety Red Teamer
Probe Mercor’s frontier AI models for safety weaknesses through adversarial testing. Find vulnerabilities and help improve model alignment.
Descriere
- Create adversarial prompts to probe frontier AI models.
- Find jailbreaks, unsafe behavior, hallucinations, and policy breaches.
- Test model resilience across misinformation, cybersecurity, biosecurity, fraud, political content, and other sensitive areas.
- Record vulnerabilities and help produce safety benchmarks and red-teaming reports.
- Partner with AI researchers to strengthen model alignment, resilience, and safety.
- Help protect and improve the next generation of frontier AI models.
- Contribute to projects that train and improve AI systems.
Cerințe
- 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
- Experience in AI red teaming, RLHF, supervised fine-tuning, AI alignment, or trust and safety is preferred
- Familiarity with jailbreak testing, prompt engineering, or adversarial evaluation methods is preferred
- Expertise in at least one sensitive domain, such as cybersecurity, biosecurity, political content, misinformation, or scientific safety, is preferred
- Must not require H-1B or STEM OPT sponsorship; Mercor cannot support candidates who need either form of sponsorship
Beneficii
- Fully remote work with a flexible schedule
- Weekly payments through Stripe or Wise for services rendered
- Project length may change or end early based on project needs and performance
- Work alongside leading AI researchers and safety teams
- Help shape how AI systems handle complex, real-world safety challenges
- Reasonable accommodations are available upon request
- Referral payments of up to $340 per successful referral, subject to limits