AI Safety Experts, English – Bengali

Mercor

AI red-teaming expert probing Mercor customer models for jailbreaks, prompt injections, bias, and misuse. Producing reproducible vulnerability data and attack cases to improve frontier AI safety.

Posted 8/14/2026contractRemote • 🇺🇸 United StatesMid-LevelSenior💰 $20 - $22 per hourWebsite

Core Competencies

Role fit

Core Competencies

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

Demonstrates expertise in red-teaming conversational AI models through adversarial testing, focusing on identifying vulnerabilities and systemic risks. Proficient in generating detailed reports and datasets while effectively communicating risks to diverse stakeholders.

Highest-signal resume keywords

Red Teaming ExperienceAdversarial TestingCybersecurity ExperienceFluent in English and BengaliAbility to Explain Risks

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

Adversarial Machine LearningPenetration TestingExploit DevelopmentReverse EngineeringSystemic Risk AnalysisVulnerability ClassificationData AnnotationPrompt Injection TechniquesBias ExploitationMulti-Turn Manipulation

Soft Skills

AdaptabilityClear Communication

Tools & Technologies

Testing FrameworksBenchmarksPlaybooks

Industry Keywords

AI Adversarial WorkSocio-Technical ProbingCreative ProbingHuman Data GenerationSystemic Risks

Tech Stack

Tools & technologies

Cyber Security

About the role

Key responsibilities & impact

Red-team conversational AI models and agents using 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
Probe AI outputs involving sensitive topics such as bias, misinformation, and harmful behaviors
Uncover vulnerabilities that automated tests miss
Expand evaluation coverage and reduce production surprises
Strengthen customer AI systems through adversarial testing

Requirements

What you’ll need

Fluent/native fluency in English and Bengali
Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
Ability to push systems to breaking points through adversarial testing
Ability to use frameworks or benchmarks rather than random hacks
Ability to explain risks clearly to technical and non-technical stakeholders
Adaptability across projects and customers
Adversarial ML experience is a nice-to-have
Cybersecurity experience such as penetration testing, exploit development, or reverse engineering is a nice-to-have
Socio-technical risk experience is a nice-to-have
Creative probing experience in psychology, acting, or writing is a nice-to-have
Must be an independent contractor
H1-B and STEM OPT candidates are not supported

Benefits

Comp & perks

Fully remote role
Flexible own schedule
Weekly payments via Stripe or Wise
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
Reasonable accommodations upon request
Higher-sensitivity project participation is optional
Clear guidelines and wellness resources for sensitive content
Referral payments of up to $90 per successful referral