AI Safety Expert – English, Bengali

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

📋 Description

• Conduct red-team evaluations of conversational AI models and agents using jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulation.

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

• Utilize taxonomies, benchmarks, and playbooks to ensure consistent testing.

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

• Analyze AI outputs related to sensitive subjects such as bias, misinformation, or harmful behaviors.

• Identify vulnerabilities that automated testing may overlook.

• Enhance evaluation coverage and minimize unexpected issues in production.

• Assist Mercor customers in improving the safety, robustness, and reliability of AI systems.

⛳️ Requirements

• Fluent or native proficiency in both English and Bengali.

• Strong discernment regarding language and content.

• Capability to evaluate whether AI responses are accurate, complete, and suitable, and to articulate the reasoning behind assessments.

• Keen ability to detect subtle errors, inconsistencies, and omissions.

• Consistent adherence to guidelines and quality standards.

• Skill in clearly explaining reasoning to both technical and non-technical audiences.

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

• Status as an independent contractor.

• Must not require H1-B or STEM OPT sponsorship.

• Preferred: experience in adversarial machine learning, including exposure to jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction.

• Preferred: background in cybersecurity, encompassing penetration testing, exploit development, or reverse engineering.

• Preferred: experience in socio-technical risks, such as harassment/disinformation probing, abuse analysis, or conversational AI evaluation.

• Preferred: qualifications in psychology, acting, or writing for innovative adversarial thinking.

🏝️ Benefits

• Fully remote position.

• Flexible schedule tailored to individual preferences.

• Weekly compensation via Stripe or Wise.

• Optional participation in higher-sensitivity projects.

• Clear guidelines and wellness resources available for sensitive-content tasks.

• Competitive salary.

• Opportunity to collaborate with top researchers.

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