AI Safety Expert – English, Tamil

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

📋 Description

• Conduct red-team assessments of conversational AI models and agents utilizing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

• Evaluate AI outputs related to sensitive subjects such as bias, misinformation, and harmful behaviors.

• Document failures, categorize vulnerabilities, and identify systemic risks.

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

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

• Investigate AI systems to reveal vulnerabilities that automated tests might overlook.

• Broaden evaluation coverage to minimize unexpected outcomes in production.

• Assist Mercor clients in enhancing the safety, robustness, and reliability of their AI systems.

⛳️ Requirements

• Proficiency in English and Tamil is mandatory.

• Strong discernment regarding language and content, including assessing whether AI responses are accurate, complete, and suitable.

• Ability to articulate reasoning clearly to both technical and non-technical audiences.

• Meticulous attention to detail, particularly with respect to subtle errors, inconsistencies, and omissions.

• Consistent adherence to taxonomies, benchmarks, playbooks, guidelines, and quality standards.

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

• Engagement as an independent contractor is required.

• Must be able to work without access to confidential or proprietary information from any other employer, client, or institution.

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

• Preferred experience in adversarial machine learning, cybersecurity, socio-technical risk, or creative probing is a plus.

🏝️ Benefits

• Fully remote position with flexible, self-directed scheduling.

• Weekly payments through Stripe or Wise based on services performed.

• Project durations may be extended, shortened, or concluded early based on needs and performance.

• Participation in higher-sensitivity projects is optional.

• Clear guidelines and wellness resources are available for work involving sensitive content.

• Competitive compensation.

• Opportunity to collaborate with top-tier researchers.

• Referral bonuses of up to $90 for each successful referral, subject to certain limits.

• Reasonable accommodations available upon request.