AI Safety Expert, English – Kannada

Mercor

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

Posted 9/20/2026contractRemote • 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 and enhancing conversational AI models through rigorous testing and analysis, with a strong focus on identifying vulnerabilities and ensuring quality standards. Proficient in generating actionable reports and datasets while maintaining fluency in English and Kannada.

Highest-signal resume keywords

Conversational AI EvaluationVulnerability IdentificationTaxonomy ApplicationAdversarial Machine LearningCybersecurity 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

JailbreaksPrompt InjectionBias ExploitationMulti-Turn ManipulationData AnnotationSystemic Risk FlaggingReproducible ReportingQuality Standards AdherenceAdversarial ML TechniquesPenetration Testing

Soft Skills

Strong JudgmentClear CommunicationAttention to DetailAdaptabilityIndependent Work

Tools & Technologies

AI ModelsTesting PlaybooksBenchmarksDatasets

Industry Keywords

Conversational AICybersecuritySocio-Technical RiskDisinformation ProbingExploit Development

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 that customers can act on
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
Work on projects training and enhancing AI systems for Mercor’s AI lab and enterprise customers

Requirements

What you’ll need

Fluent/native fluency in English and Kannada required
Strong judgment about language and content, including evaluating whether AI responses are accurate, complete, and appropriate
Ability to explain reasoning clearly to technical and non-technical audiences
Rigorous attention to subtle errors, inconsistencies, and gaps
Ability to follow taxonomies, benchmarks, playbooks, guidelines, and quality standards consistently
Ability to adapt across projects, task types, and customers
Independent contractor status
Must not be an H1-B or STEM OPT candidate
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 that can be completed on your own schedule
Weekly payments via Stripe or Wise based on services rendered
Opportunity to build experience in human data-driven AI red teaming at the frontier of safety
Direct role in making AI systems more robust, safe, and trustworthy
Wellness resources and clear guidelines for higher-sensitivity projects
Reasonable accommodations upon request
Referral payments of up to $90 for each successful referral, subject to restrictions