AI Safety Expert, English – Bengali

atMercorRemoteUS flagUnited StatesFreelanceArtificial IntelligenceMid-levelSenior$20 – $22/hour

Posted Aug 27

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

πŸ“‹ Description

β€’ Conduct red-team assessments on conversational AI models and agents.

β€’ Evaluate jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

β€’ Document AI failures, categorize vulnerabilities, and identify systemic risks.

β€’ Utilize taxonomies, benchmarks, and playbooks to ensure consistent testing methodologies.

β€’ Create reproducible reports, datasets, and attack cases for clients.

β€’ Uncover vulnerabilities that automated testing may overlook.

β€’ Enhance evaluation scope and minimize unexpected issues in production.

β€’ Assist Mercor clients in fortifying the safety, robustness, and reliability of their AI systems.

β€’ Engage in projects focused on training and improving advanced AI systems.


⛳️ Requirements

β€’ Native or fluent proficiency in both English and Bengali is essential.

β€’ Previous experience in red teaming within AI adversarial roles, cybersecurity, or socio-technical analysis.

β€’ Capability to probe AI systems in an adversarial manner, including jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulations.

β€’ Proficiency in generating human data by documenting failures, categorizing vulnerabilities, and identifying systemic risks.

β€’ Competence in adhering to taxonomies, benchmarks, and playbooks.

β€’ Ability to produce reproducible reports, datasets, and attack scenarios.

β€’ Skill in clearly communicating risks to both technical and non-technical audiences.

β€’ Flexibility to adapt across various projects and clients.

β€’ H1-B and STEM OPT candidates are not eligible.

β€’ Engagement as an independent contractor.


🏝️ Benefits

β€’ Fully remote position that allows for a flexible schedule.

β€’ Weekly payments through Stripe or Wise based on services provided.

β€’ Participation in higher-sensitivity projects is optional.

β€’ Access to clear guidelines and wellness resources for higher-sensitivity initiatives.

β€’ Competitive compensation.

β€’ Referral bonus of up to $90 for each successful referral.

β€’ Unlimited referrals allowed (certain restrictions may apply).

People also viewed

WON.ai20 hours ago

AI Strategist

AR flagArgentina OnlyFreelanceArtificial Intelligence
ApplyView job
The College Board21 hours ago

Director, AI Assisted Solutions

US flagUnited States OnlyFull-timeArtificial Intelligence$88k – $135k/year
ApplyView job
Mercor22 hours ago

AI Safety Experts – English, Assamese

US flagUnited States OnlyFreelanceArtificial Intelligence$16 – $22/hour
ApplyView job
Mercor22 hours ago

AI Safety Experts – English, Marathi

US flagUnited States OnlyFreelanceArtificial Intelligence$16 – $22/hour
ApplyView job
Mercor22 hours ago

AI Safety Expert – English, Bengali

US flagUnited States OnlyFreelanceArtificial Intelligence$16 – $22/hour
ApplyView job
Gartner22 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