Freelancer - GenAI Experts

Alice • New York, NY

8d

About The Position

We are seeking versatile GenAI Specialists to join our expert collective. This role encompasses two complementary focus areas—and we're looking for individuals who excel in one or both:
Focus Area 1: Adversarial Analysis
Design and execute adversarial prompts to identify weaknesses in cutting-edge AI systems, including LLMs, Text-to-Image, Text-to-Video, Multi-Modal models, and AI Agents. Analyze outputs, categorize vulnerabilities, and translate findings into actionable safety insights.
Focus Area 2: Creative Prompt Design
Craft diverse, context-rich prompts that challenge AI models across policy domains. Blend linguistic creativity with sociocultural insight to simulate realistic, localized use cases - from benign edge cases to sophisticated deception attempts.

Requirements

• Proven experience with Generative AI models (direct technical experience not required)
• Understanding of risk taxonomies (e.g., harm categories, policy tiers)
• Strong attention to detail and organizational capabilities
• Ability to manage multiple tasks simultaneously and meet deadlines
• Ability to balance creativity with policy sensitivity

Nice To Haves

• Strong creative writing background (journalism, fiction, or linguistics)
• Familiarity with various model types (Text-to-Text, Text-to-Image, Text-to-Video)
• Experience with prompt injection techniques, jailbreaks, and red-teaming methodologies
• Prior work in model evaluation, prompt engineering, or safety analysis
• Regional expertise or cultural fluency in specific geopolitical areas
• Proficiency in one or more non-English languages

Responsibilities

• Design adversarial prompts to test AI systems across multiple modalities
• Identify, categorize, and document model weaknesses or unsafe outputs
• Support data annotation, curation, and quality control processes
• Summarize findings into structured reports or data templates
• Produce high-quality, diverse prompt sets reflecting global linguistic and cultural nuances
• Research online behaviors of threat actors to inform realistic prompt design
• Cover multiple policy areas, such as Hate Speech, Sexual/Graphic Harm, or Terrorism
• Adapt prompts for multiple languages and dialects where applicable

What This Job Offers

• Career Level: Mid Level
• Education Level: No Education Listed
• Number of Employees: 251-500 employees