Bilingual italian expert - ai safety
pbLuogo di lavoro: /b Roma /ph3About the job /h3pbMercor /b connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include bBenchmark /b, bGeneral Catalyst /b, bPeter Thiel /b, bAdam D'Angelo /b, bLarry Summers /b, and bJack Dorsey /b. /ppbPosition: /b Bilingual Italian Generalist Expert - AI Safetybr/bType: /b bContract /bbr/bCompensation: /b b$40-$44/hour /bbr/bLocation: /b bRemote /b /ph3Role Responsibilities /h3ulliWrite expert-level prompts in bItalian /b across a range of sensitive subject areas. /liliApply structured guidelines to classify prompts and conversations. /liliFlag adversarial phrasings and escalation patterns. Document the reasoning behind your judgments. /liliEvaluate and strengthen how bAI models /b handle sensitive topics in bItalian /b. /liliWork bindependently and asynchronously /b to improve bAI model safety /b.
/li /ulh3Qualifications /h3h3Must-Have /h3ulliNative or near-native fluency in bItalian /b. Business-level written bEnglish /b. /liliA bBachelor's degree /b, completed or in progress. /liliStrong written reasoning and high attention to detail. /liliSound judgment around sensitive and dual-use information. /li /ulh3Preferred /h3ulliBased in bItaly /b or the wider bWestern Europe /b region. /liliExperience reviewing, grading, or red-teaming written or technical content. /liliBackground in trust and safety, content moderation, policy evaluation, or adversarial testing. /li /ulh3Start Date /h3ullibImmediate /b /li /ulh3Resources Support /h3ulliFor details about the interview process and platform information, please check: /liliFor any help or support, reach out to: (per questa informazione, accedi alle sezione INFO E CANDIDATURE) /li /ul #J-18808-Ljbffr
/li /ulh3Qualifications /h3h3Must-Have /h3ulliNative or near-native fluency in bItalian /b. Business-level written bEnglish /b. /liliA bBachelor's degree /b, completed or in progress. /liliStrong written reasoning and high attention to detail. /liliSound judgment around sensitive and dual-use information. /li /ulh3Preferred /h3ulliBased in bItaly /b or the wider bWestern Europe /b region. /liliExperience reviewing, grading, or red-teaming written or technical content. /liliBackground in trust and safety, content moderation, policy evaluation, or adversarial testing. /li /ulh3Start Date /h3ullibImmediate /b /li /ulh3Resources Support /h3ulliFor details about the interview process and platform information, please check: /liliFor any help or support, reach out to: (per questa informazione, accedi alle sezione INFO E CANDIDATURE) /li /ul #J-18808-Ljbffr