GenAI Safety Analyst

This is a fully remote position, open to applicants in United States.

📋 Description

• Evaluate content violations to assist in securing Generative AI tools.

• Collaborate with specialists in areas such as Hate Speech, Misinformation, Intellectual Property, Copyright, and other forms of abuse.

• Create adversarial prompts to pinpoint vulnerabilities in LLMs, Text-to-Image, Text-to-Video, AI Agents, and other AI models.

• Supervise data management to guarantee high-quality outcomes.

• Design adversarial and high-risk prompt strategies across various abuse areas to reveal model weaknesses.

• Oversee projects from inception to completion, ensuring quality assurance and timely delivery.

• Manage large datasets across diverse languages and abuse categories.

• Explore new methods for bypassing the safety measures of foundational models.

• Collaborate with engineering, product, and policy teams to tackle challenges and devise strategies and solutions.

• Encourage knowledge sharing and continuous learning within the team.

⛳️ Requirements

• Experience in AI Safety and/or Responsible AI and/or Trust and Safety.

• Knowledge of contemporary Generative AI models and agents is crucial.

• Proficiency in English at a near-native level.

• Strong attention to detail.

• Excellent organizational skills.

• Ability to manage multiple tasks simultaneously.

• Experience with various model types (Text-to-Text, Text-to-Image) is preferred.

• Previous experience with OSINT (Open Source Intelligence) will be advantageous.

• A self-motivated attitude and the drive to thrive in a dynamic and fast-paced environment.

🏝️ Benefits

• Opportunity for professional growth and development.

• Collaborative and innovative work environment.

• Competitive compensation and benefits package.