AI Safety Expert, English, Odia

Mercor

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

Posted 9/19/2026contractRemote • 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 through adversarial testing, vulnerability assessment, and systematic evaluation of AI outputs. Proficient in generating human data and producing reproducible reports while maintaining rigorous quality standards.

Highest-signal resume keywords

Adversarial TestingVulnerability AssessmentHuman Data AnnotationFluency in English and OdiaAttention to Detail

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 ExploitationMulti-Turn ManipulationSystemic Risk AnalysisTaxonomy ApplicationBenchmarkingReport ProductionDataset CreationAdversarial Machine Learning

Soft Skills

Strong JudgmentClear CommunicationAdaptabilityAttention to Subtle Errors

Industry Keywords

CybersecuritySocio-Technical RiskCreative ProbingQuality StandardsGuideline Adherence

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
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
Strengthen customer AI systems through adversarial testing

Requirements

What you’ll need

Native fluency in English and Odia
Strong judgment about language and content
Ability to assess whether AI responses are accurate, complete, and appropriate, and explain why
Rigorous attention to 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 status
H1-B and STEM OPT candidates are not supported
Nice-to-have specialties include adversarial ML, cybersecurity, socio-technical risk, and creative probing

Benefits

Comp & perks

Fully remote work
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
Wellness resources and clear guidelines for higher-sensitivity projects
Referral payments of up to $90 per successful referral
Reasonable accommodations upon request
Opportunity to collaborate with leading researchers
Opportunity to work on frontier AI safety projects