AI Safety Expert – English, Odia

Mercor

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

Posted 9/23/2026contractRemote • 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 red-teaming conversational AI models and agents, with a focus on identifying vulnerabilities and ensuring the safety and robustness of AI systems. Proficient in generating human data through annotation and classification while adhering to quality standards and guidelines.

Highest-signal resume keywords

Red-Team Conversational AI ModelsAdversarial ML ExperienceNative Fluency in English and OdiaCybersecurity ExperienceAbility to Assess AI Responses

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

JailbreaksPrompt InjectionsBias ExploitationMulti-Turn ManipulationVulnerability ClassificationSystemic Risk FlaggingReproducible ReportingDataset ProductionPenetration TestingExploit Development

Soft Skills

Strong Judgment About LanguageAttention to DetailClear CommunicationAdaptabilityIndependent Work

Industry Keywords

Conversational AI TestingSocio-Technical RiskHarassment ProbingDisinformation AnalysisQuality Standards

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 that automated tests miss
Expand evaluation coverage and reduce production surprises
Help customers strengthen the safety and robustness of their AI systems

Requirements

What you’ll need

Native fluency in English and Odia is required
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
Must not require H1-B or STEM OPT support
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
Work on your own schedule
Weekly payments via Stripe or Wise
Projects may be extended, shortened, or concluded early depending on needs and performance
Wellness resources and clear guidelines for higher-sensitivity projects
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
Competitive pay
Referral payments of up to $90 for each successful referral (referral limits apply)