AI Safety Expert – English, Marathi

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

📋 Description

• Conduct red-team assessments of conversational AI models and agents through methods such as jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation.

• Create human data by annotating failures, classifying vulnerabilities, and identifying systemic risks.

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

• Generate reproducible reports, datasets, and attack case studies.

• Evaluate AI outputs related to sensitive subjects, including bias, misinformation, or harmful behaviors.

• Assist in broadening evaluation coverage and enhancing customer AI systems.

• Engage in projects focused on training and improving frontier AI models.

⛳️ Requirements

• Native fluency in both English and Marathi is essential.

• Strong judgment regarding language and content is necessary.

• Capacity to assess the accuracy, completeness, and appropriateness of AI responses, along with the ability to explain the rationale.

• Skill in identifying subtle errors, inconsistencies, and gaps.

• Consistent adherence to guidelines and quality standards is required.

• Proficient at clearly articulating reasoning to both technical and non-technical audiences.

• Flexibility to adapt across various projects, task types, and client needs.

• Must possess independent contractor status.

• H1-B and STEM OPT candidates are not eligible for this position.

🏝️ Benefits

• Fully remote position.

• Flexible working hours; complete tasks on your own schedule.

• Receive weekly payments via Stripe or Wise.

• Competitive compensation offered.

• Collaborate with leading researchers in the field.

• Access to wellness resources and clear guidelines for projects with higher sensitivity.

• Reasonable accommodations available upon request.

• Earn up to $90 per successful referral as a bonus.