AI Safety Experts – English, Malay

Mercor

AI red teaming expert probing frontier models for Mercor, which partners with AI labs and enterprises to train advanced models. Generating reproducible attack data and vulnerability reports to improve AI safety and robustness.

Posted 8/9/2026contractRemote • 🇺🇸 United StatesMid-LevelSenior💰 $17 - $25 per hourWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in red teaming AI systems, focusing on adversarial testing, vulnerability identification, and risk communication. Proficient in generating human data and producing reproducible reports to enhance AI safety and robustness.

Highest-signal resume keywords

Red Teaming ExperienceAdversarial TestingVulnerability ClassificationRisk CommunicationNative Fluency in English and Malay

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 Machine LearningJailbreak DatasetsPrompt InjectionRLHF/DPO AttacksPenetration TestingExploit DevelopmentReverse EngineeringConversational AI TestingSystemic Risk AnalysisFailure Annotation

Soft Skills

AdaptabilityCreative ProbingClear Communication

Tools & Technologies

TaxonomiesBenchmarksPlaybooks

Industry Keywords

CybersecuritySocio-Technical ProbingDisinformation AnalysisAbuse Analysis

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
Probe AI systems to uncover vulnerabilities automated tests miss
Expand evaluation coverage and reduce production surprises
Support Mercor customers in improving the safety and robustness of their AI systems

Requirements

What you’ll need

Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing
Ability to push systems to breaking points through adversarial testing
Experience using frameworks or benchmarks rather than random hacks
Ability to explain risks clearly to technical and non-technical stakeholders
Adaptability across projects and customers
Native fluency in English and Malay
Adversarial ML experience such as jailbreak datasets, prompt injection, RLHF/DPO attacks, or model extraction is a nice-to-have
Cybersecurity specialties such as penetration testing, exploit development, or reverse engineering are a nice-to-have
Socio-technical risk specialties such as harassment/disinformation probing, abuse analysis, or conversational AI testing are a nice-to-have
Creative probing experience in psychology, acting, or writing is a nice-to-have
Must not be an H1-B or STEM OPT candidate

Benefits

Comp & perks

Fully remote role
Flexible own schedule
Higher-sensitivity project participation is optional
Clear guidelines and wellness resources for sensitive-content projects
Weekly payments via Stripe or Wise
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