GenAI Safety Analyst
Posted 1hrs ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
GenAI Safety Analyst analyzing AI risks, adversarial prompts, and model vulnerabilities. Supporting Alice’s trust, safety, and security solutions for frontier AI platforms.
Responsibilities:
- Analyze content infringements to help secure Generative AI tools
- Collaborate with experts in Hate Speech, Misinformation, Intellectual Property, Copyright, and other abuse areas
- Write adversarial prompts to identify weaknesses in LLMs, Text-to-Image, Text-to-Video, AI Agents, and other AI models
- Oversee data management to ensure high-quality outputs
- Develop adversarial and risky prompt strategies across abuse areas to expose model vulnerabilities
- Manage projects end-to-end from planning and oversight through quality assurance to final delivery
- Handle extensive datasets across multiple languages and abuse areas
- Investigate new tactics for circumventing foundational models' safety measures
- Work with engineering, product, and policy teams to address challenges and develop strategies and solutions
- Promote knowledge exchange and continual learning within the team
Requirements:
- Background in AI Safety and/or Responsible AI and/or Trust and Safety
- Familiarity with recent Generative AI models and agents is essential
- Command of English at a near-native level
- Attention to detail
- Organizational capabilities
- Capacity to juggle numerous tasks concurrently
- Experience with various model types (Text-to-Text, Text-to-Image) is desirable
- Prior experience with OSINT (Open Source Intelligence) will be considered an asset
- Self-starter attitude and energy to excel in a fast-moving and variable environment




















