AI Safety Expert, English, Portuguese

Mercor

AI safety experts red teaming conversational models for Mercor’s human-data AI projects. Probing vulnerabilities and generating reproducible datasets to improve frontier AI safety.

Posted 8/23/2026contractRemote • 🇺🇸 United StatesMid-LevelSenior💰 $29 - $45 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 probing vulnerabilities and biases. Proficient in generating reports and datasets while collaborating with researchers to enhance AI systems.

Highest-signal resume keywords

Red Teaming ExperienceJailbreaks and Prompt InjectionsVulnerability ClassificationReproducible ReportingFluency in English and Portuguese

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

Conversational AI ModelsBias ExploitationMulti-Turn ManipulationSystemic Risk FlaggingTaxonomies and BenchmarksData AnnotationAttack Case ProductionCybersecurity ProbingAdversarial WorkMisinformation Probing

Soft Skills

Clear CommunicationAdaptability

Industry Keywords

AI SystemsSocio-Technical ProbingTesting PlaybooksFailure AnnotationEvaluation Coverage

Tech Stack

Tools & technologies

Cyber Security

About the role

Key responsibilities & impact

Red team conversational AI models and agents
Test 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 maintain consistent testing
Produce reproducible reports, datasets, and attack cases for customers
Probe sensitive topics including bias, misinformation, and harmful behaviors
Help expand evaluation coverage and reduce production surprises
Collaborate with leading researchers on projects training and enhancing AI systems

Requirements

What you’ll need

Native fluency in English and Portuguese (global, excluding Brazilian Portuguese)
Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
Ability to probe AI models using jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation
Ability to annotate failures, classify vulnerabilities, and flag systemic risks
Ability to follow taxonomies, benchmarks, and playbooks
Ability to produce reproducible reports, datasets, and attack cases
Ability to explain risks clearly to technical and non-technical stakeholders
Adaptability across projects and customers
H1-B and STEM OPT candidates are not supported

Benefits

Comp & perks

Fully remote role
Flexible, self-directed schedule
Weekly payments via Stripe or Wise
Higher-sensitivity project participation is optional
Clear content guidelines and wellness resources
Opportunity to build experience in human data-driven AI red teaming
Direct role in making AI systems more robust, safe, and trustworthy
Competitive pay
Collaboration with leading researchers
Referral payments of up to $180 per successful referral