GenAI Safety & Adversarial Analyst

ActiveFence Ltd.; États-Unis; À distance; USD 63 000 - 90 000; Plein temps

Résumé du poste

Alice is seeking a driven, detail-focused professional to become a vital part of our team as a Generative AI Analyst. In this role, you'll dive into the cutting-edge of technology, analyzing content infringements and safeguarding the AI era.

You’ll write adversarial prompts to probe models, oversee data quality, and collaborate with experts across Hate Speech, Misinformation, IP and Copyright. A strong bias for safety and thoroughness is essential.

Qualifications

• Background in AI Safety and/or Responsible AI and/or Trust and Safety.
• Familiarity with recent Generative AI models and agents.
• Near-native English fluency.
• Strong organizational skills and ability to juggle multiple tasks.

Responsabilités

• Develop adversarial prompt strategies to expose vulnerabilities in models.
• Manage projects end-to-end from planning to final delivery.
• Handle large multilingual datasets with precision.
• Investigate new tactics to circumnavigate safety measures.
• Collaborate with engineering, product, policy teams to tackle challenges.
• Promote knowledge exchange and continual learning.

Connaissances

Attention to detail

English proficiency

Self-starter

Formation

Background in AI Safety / Responsible AI / Trust and Safety

Description du poste

Alice is seeking a driven, detail-focused professional to become a vital part of our team as a Generative AI Analyst. In this role, you'll dive into the cutting-edge of technology, analyzing content infringements and safeguarding the AI era.

You’ll write adversarial prompts to probe models, oversee data quality, and collaborate with experts across Hate Speech, Misinformation, IP and Copyright. A strong bias for safety and thoroughness is essential.