AI Safety Experts, English – Gujarati

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

📋 Description

• Conduct red-team evaluations on conversational AI models and agents through jailbreak techniques, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

• Generate human data by annotating failures, categorizing vulnerabilities, and identifying systemic risks.

• Implement taxonomies, benchmarks, and playbooks to ensure consistent testing practices.

• Create reproducible reports, datasets, and attack cases for client use.

• Analyze AI outputs related to sensitive subjects such as bias, misinformation, and harmful behavior.

• Expose vulnerabilities that automated tests may overlook.

• Enhance evaluation coverage and minimize unexpected issues during production.

• Collaborate on initiatives that train and improve frontier AI systems.

⛳️ Requirements

• Fluent or native proficiency in both English and Gujarati is essential.

• Possess strong judgment regarding language and content; capable of evaluating the accuracy, completeness, and appropriateness of AI responses.

• Ability to detect subtle errors, inconsistencies, and gaps in information.

• Consistently adhere to guidelines and quality standards.

• Capable of articulating reasoning effectively to both technical and non-technical audiences.

• Adaptable across various projects, task types, and client needs.

• Engagement as an independent contractor is required.

• Candidates must not be on an H1-B or STEM OPT visa.

• Nice-to-have: experience in adversarial machine learning, including knowledge of jailbreak datasets, prompt injections, RLHF/DPO attacks, and model extraction.

• Nice-to-have: background in cybersecurity, encompassing penetration testing, exploit development, and reverse engineering.

• Nice-to-have: experience in socio-technical risk assessment, including probing for harassment/disinformation, abuse analysis, and conversational AI testing.

• Nice-to-have: background in psychology, acting, or writing to foster unconventional adversarial thinking.

🏝️ Benefits

• Fully remote position.

• Flexible working hours; manage your own schedule.

• Receive weekly payments through Stripe or Wise.

• Optional participation in higher-sensitivity projects.

• Access to clear guidelines and wellness resources for working with sensitive content.

• Competitive compensation.

• Reasonable accommodations available upon request.

• Referral opportunity with earnings of up to $90 for each successful referral (subject to limits).