Job description
Description
Alice.io (formerly known as ActiveFence) is a leading trust, safety, and security company. Just like 'Alice' herself, we go down the rabbit hole into the emerging world of AI and focus on safeguarding these technologies. In a world where AI has fundamentally changed the nature of risk, Alice offers coverage across the entire AI lifecycle.
We're currently on the ground floor of an exciting new initiative: building an "Elite Collective" of the world's premier GenAI experts—high-stakes, project-based work for the "best of the best" specialists in the industry.
Work is on-demand and project-dependent, scaling up and down based on the needs of the client. This is not a high-volume, repetitive role; it is an opportunity to be tapped for specific, high-impact interventions when your unique expertise is required.
The most sophisticated technology challenges in the world are waiting down the rabbit hole. We're looking for the sharpest minds to help us secure the frontier.
The invitation is open: Come join us at the tea party.
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.
Key Responsibilities
Adversarial Analysis:
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
Creative Prompt Design:
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
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
Language Requirements
For Creative Prompt Design focus: We are actively seeking native speakers in the following languages:
English | Italian | Spanish | German | French | Japanese | Chinese (Mandarin) | Korean | Arabic
Native-level fluency is essential for crafting culturally authentic, nuanced prompts that reflect real-world linguistic patterns and regional contexts.
Preferred Qualifications
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
All applicants will be required to complete a screening exam and background check.
Originally posted on Himalayas
Who can apply
Eligible countries: United States. Accepted UTC offsets: UTC-10, UTC-9, UTC-8, UTC-7, UTC-6, UTC-5, UTC+14. Review the full description for employer-specific work authorization, residency and schedule requirements.