About this role
Accountabilities:
- Design and execute authorized adversarial test scenarios to evaluate AI systems against defined content safety policies and compliance requirements.
- Develop diverse, challenging, and unexpected prompts, inputs, and situations designed to test system behavior.
- Explore edge cases, unusual inputs, complex contexts, and different user behaviors that may expose gaps in safety controls.
- Evaluate AI-generated responses and identify potential weaknesses, inconsistencies, policy concerns, or failures in enforcement.
- Test system behavior across different forms of language, context, intent, and communication styles.
- Identify recurring patterns and scenarios that may require additional investigation, testing, or system improvement.
- Clearly document test scenarios, system responses, findings, and supporting evidence.
- Apply project requirements, testing methodologies, and content safety guidelines consistently.
- Review complex or ambiguous cases and apply sound judgment when evaluating system behavior.
- Maintain high standards of accuracy, consistency, documentation quality, and attention to detail across assigned evaluations.
Requirements:
- Educational background or equivalent experience in Trust & Safety, Content Safety, Policy, Linguistics, Communications, Journalism, Research, AI Evaluation, or a related field.
- Relevant experience in content safety, trust and safety, AI evaluation, content moderation, policy enforcement, quality assurance, or a related discipline.
- Strong understanding of content safety principles, policy enforcement, and common safety risks.
- Strong written English comprehension and communication skills, with the ability to understand nuanced language and context.
- Strong understanding of user intent, contextual meaning, and the different ways people may communicate.
- Ability to think creatively and develop challenging, unusual, or unexpected test scenarios.
- Strong analytical and critical-thinking skills, with the ability to identify patterns, weaknesses, inconsistencies, and behavioral gaps.
- Comfort working with complex or ambiguous situations and making informed decisions based on defined requirements.
- Ability to understand and consistently apply detailed testing guidelines and policies.
- Strong documentation skills and exceptional attention to detail.
- Familiarity with AI systems, large language models, adversarial testing, red teaming, or AI safety is preferred.
- Ability to work independently while maintaining consistent quality across a high volume of evaluation tasks.
Benefits:
- Compensation: US$13 per hour.
- Contract type: Freelance, with potential opportunity to transition into a full-time role.
- Location: India.
- Language: English.
- Flexibility: Freelance structure offering flexibility in managing assigned work.
- Professional exposure: Hands-on experience evaluating AI systems, content safety controls, and policy compliance.
- Impact: Contribute to identifying safety gaps and improving the reliability of AI-powered systems.
- Skill development: Opportunity to strengthen expertise in AI evaluation, adversarial testing, trust and safety, and policy analysis.
How Jobgether works:
We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.
We appreciate your interest and wish you the best!
Why Apply Through Jobgether?
Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.
#LI-CL1