AI Safety Expert, English, Dutch

Mercor

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

Posted 9/22/2026contractRemote • United StatesMid-LevelSenior💰 $48 - $62 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 systems through adversarial testing, including the identification of vulnerabilities and the application of structured testing frameworks. Proficient in communicating risks to diverse stakeholders while maintaining adaptability across various projects and clients.

Highest-signal resume keywords

Red Teaming ExperienceAdversarial MLCybersecurityFluent in English and DutchStructured Testing Frameworks

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 TestingPrompt InjectionJailbreak DatasetsPenetration TestingExploit DevelopmentModel ExtractionBias ExploitationFailure AnnotationVulnerability ClassificationRisk Flagging

Soft Skills

Clear CommunicationAdaptability

Tools & Technologies

TaxonomiesBenchmarksPlaybooks

Industry Keywords

Conversational AISocio-Technical ProbingDisinformation ProbingHarmful BehaviorsSystemic Risks

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 maintain consistent testing
Produce reproducible reports, datasets, and attack cases for customers
Review AI outputs involving sensitive topics such as bias, misinformation, and harmful behaviors
Identify 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 Dutch
Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
Ability to probe AI systems adversarially and push them to breaking points
Experience using frameworks, taxonomies, benchmarks, or playbooks for structured testing
Ability to explain risks clearly to technical and non-technical stakeholders
Adaptability across projects and customers
Independent contractor status
Must not require H1-B or STEM OPT support
Nice-to-have specialties: adversarial ML, cybersecurity, socio-technical risk, or creative probing
Adversarial ML experience may include jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction
Cybersecurity experience may include penetration testing, exploit development, or reverse engineering
Socio-technical risk experience may include harassment/disinformation probing, abuse analysis, or conversational AI testing
Creative probing experience may include psychology, acting, or writing

Benefits

Comp & perks

Fully remote role
Flexible schedule; work can be completed 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
Competitive payment
Referral bonus of up to $250 for each successful referral, subject to limits
Reasonable accommodations available upon request