AI Safety Expert – English, Gujarati

atMercorRemoteUS flagUnited StatesFreelanceArtificial IntelligenceMid-levelSenior$16 – $22/hour

Posted Sep 19

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

📋 Description

• Conduct red-team evaluations of conversational AI models and agents through the use of jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

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

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

• Generate reproducible reports, datasets, and examples of attacks.

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

• Identify vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage and minimize unexpected outcomes in production.

• Enhance customer AI systems through systematic adversarial testing.


⛳️ Requirements

• Native proficiency in English and Gujarati is essential.

• Strong judgment in evaluating language and content.

• Capability to determine the accuracy, completeness, and appropriateness of AI responses, along with the ability to articulate reasoning.

• Keen eye for detecting subtle errors, inconsistencies, and omissions.

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

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

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

• Status as an independent contractor is required.

• Candidates must not hold H1-B or STEM OPT status.

• Preferred areas of expertise include adversarial machine learning, cybersecurity, socio-technical risks, or creative probing.


🏝️ Benefits

• Fully remote position.

• Flexible working hours, allowing you to set your own schedule.

• Weekly compensation through Stripe or Wise.

• Access to wellness resources and clear protocols for sensitive projects.

• Reasonable accommodations available upon request.

• Competitive compensation package.

• Referral bonuses of up to $90 for each successful referral (program benefit).

People also viewed

WON.ai17 hours ago

AI Strategist

AR flagArgentina OnlyFreelanceArtificial Intelligence
ApplyView job
The College Board18 hours ago

Director, AI Assisted Solutions

US flagUnited States OnlyFull-timeArtificial Intelligence$88k – $135k/year
ApplyView job
Mercor19 hours ago

AI Safety Experts – English, Assamese

US flagUnited States OnlyFreelanceArtificial Intelligence$16 – $22/hour
ApplyView job
Mercor19 hours ago

AI Safety Experts – English, Marathi

US flagUnited States OnlyFreelanceArtificial Intelligence$16 – $22/hour
ApplyView job
Mercor19 hours ago

AI Safety Expert – English, Bengali

US flagUnited States OnlyFreelanceArtificial Intelligence$16 – $22/hour
ApplyView job
Gartner19 hours ago

Director, Analyst – AI Technology Economics

GB flagUnited Kingdom OnlyFull-timeArtificial Intelligence
ApplyView job

Never miss a great job!

Get handpicked remote jobs straight to your inbox weekly.

Trusted by 7,400+ designers