AI Safety Experts – English, Bengali

Mercor

. Red team conversational AI models and agents through jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation .

Posted 9/24/2026contractRemote • United StatesMid-LevelSenior💰 $16 - $22 per hourWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in evaluating conversational AI models and agents, focusing on identifying vulnerabilities and biases while producing comprehensive reports and datasets. Proficient in assessing AI outputs for accuracy and appropriateness, with strong communication skills for diverse audiences.

Highest-signal resume keywords

Native Fluency In EnglishNative Fluency In BengaliAdversarial ML ExperienceCybersecurity ExperienceSocio-Technical Risk Experience

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Red TeamingPrompt InjectionBias ExploitationVulnerability ClassificationAutomated TestingAdversarial Machine LearningPenetration TestingExploit DevelopmentConversational AI TestingData Annotation

Soft Skills

Strong JudgmentAttention To DetailClear CommunicationAdaptabilityIndependent Work

Industry Keywords

JailbreaksMulti-Turn ManipulationSystemic RisksQuality StandardsGuidelines ComplianceHarassment ProbingDisinformation AnalysisConversational AIRLHFDPO Attacks

Tech Stack

Tools & technologies

Cyber Security

About the role

Key responsibilities & impact

Red team conversational AI models and agents through jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
Generate human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
Apply taxonomies, benchmarks, and playbooks to keep testing consistent
Produce reproducible reports, datasets, and attack cases for customers
Review AI outputs involving sensitive topics such as bias, misinformation, or harmful behaviors
Uncover vulnerabilities automated tests miss
Expand evaluation coverage and reduce production surprises

Requirements

What you’ll need

Native fluency in English and Bengali
Strong judgment about language and content; ability to assess whether AI responses are accurate, complete, and appropriate and explain why
Ability to notice subtle errors, inconsistencies, and gaps
Ability to follow guidelines and quality standards consistently
Ability to explain reasoning clearly to technical and non-technical audiences
Adaptability across projects, task types, and customers
Independent contractor engagement
H1-B and STEM OPT candidates are not supported
Nice-to-have: adversarial ML experience, including jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction
Nice-to-have: cybersecurity experience, including penetration testing, exploit development, or reverse engineering
Nice-to-have: socio-technical risk experience, including harassment/disinformation probing, abuse analysis, or conversational AI testing
Nice-to-have: psychology, acting, or writing experience for unconventional adversarial thinking

Benefits

Comp & perks

Fully remote role
Flexible schedule / work on your own schedule
Weekly payments via Stripe or Wise
Projects may be extended, shortened, or concluded early depending on needs and performance
Reasonable accommodations upon request
Opportunity to build experience in human data-driven AI red teaming
Direct role in making AI systems more robust, safe, and trustworthy
Collaboration with leading researchers
Referral payments of up to $90 per successful referral, subject to limits