Bilingual Adversarial AI Quality Engineer

About the jobMercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco our investors include Benchmark General Catalyst Peter Thiel Adam DAngelo Larry Summers and Jack Dorsey.PositionRed Team SpecialistType: Full-time or Part-time Contract WorkCompensation: $32/hourLocation: RemoteCommitment: 20 hours/weekRole ResponsibilitiesEvaluate conversational AI models for jailbreaks prompt injections and misuse cases.Generate high-quality human data by annotating failures and classifying vulnerabilities.Apply structured taxonomies and benchmarks to maintain consistent testing.Document reproducibly by producing reports datasets and actionable attack cases.Collaborate with stakeholders to communicate risks clearly and effectively.Work independently and asynchronously to enhance AI model safety.QualificationsMust-HaveFluent English & Arabic language skills.Prior experience in AI adversarial work cybersecurity or socio-technical probing.Strong communication skills for technical and non-technical stakeholders.Ability to adapt across projects and customer needs.PreferredExperience with adversarial ML cybersecurity or socio-technical risk.Skills in creative probing such as psychology acting or unconventional adversarial thinking.Compensation & LegalHourly contractorPaid weeklyApplication Process (Takes 2030 mins to complete)Upload resumeAI interview based on your resumeSubmit formResources & SupportFor details about the interview process and platform information please check:For any help or support reach out to:PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.#J-18808-Ljbffr