AI Safety Experts, English – Kannada

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

📋 Description

• Conduct red-team exercises on conversational AI models and agents by utilizing jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.

• Create human data through the annotation of failures, classification of vulnerabilities, and identification of systemic risks.

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

• Generate reproducible reports, datasets, and attack scenarios for clients.

• Investigate AI outputs for biases, misinformation, and harmful behaviors.

• Broaden evaluation coverage while identifying vulnerabilities that automated tests may overlook.

• Assist in training and refining advanced AI systems for Mercor’s clientele.

⛳️ Requirements

• Native proficiency in both English and Kannada.

• Strong judgment regarding language and content quality.

• Capability to evaluate the accuracy, completeness, and appropriateness of AI responses.

• Proficiency in clearly articulating reasoning to both technical and non-technical audiences.

• Meticulous attention to detail, including subtle errors, inconsistencies, and gaps.

• Consistent adherence to guidelines and quality standards.

• Flexibility in adapting to different projects, task types, and client needs.

• Status as an independent contractor.

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

• Preferred experience in adversarial ML, cybersecurity, socio-technical risk, or creative probing.

🏝️ Benefits

• Fully remote work arrangement.

• Flexibility to create your own schedule.

• Weekly payments processed through Stripe or Wise.

• Competitive compensation.

• Optional involvement in higher-sensitivity projects.

• Clear content guidelines along with wellness resources.

• Reasonable accommodations available upon request.

• Referral bonuses of up to $90 for each successful referral.