Italian Language Expert - AI Safety

Obsidian; Roma; In loco; EUR 28.000 - 38.000; Tempo pieno

Descrizione del lavoro

Obsidian is hiring proficient bilingual speakers (Italian & English) to help make advanced AI models safer. You will apply language fluency and cultural judgment to evaluate how models handle sensitive topics in Italian.

No prior AI/ML experience required — we will train you on the workflow. You will write expert-level prompts in Italian, apply guidelines to classify content, and flag adversarial phrasing with clear rationale.

Competenze

• Native or near-native Italian with business English proficiency.
• Bachelor's degree or in progress.
• Strong written reasoning and attention to detail.
• Good judgment around sensitive information.

Mansioni

• Write expert-level prompts in Italian across topics.
• Apply guidelines to classify prompts and conversations.
• Flag adversarial phrasing and document reasoning.

Conoscenze

Italian fluency

Business English

Formazione

Bachelor's degree, in progress

Descrizione del lavoro

About the role

We're hiring proficient bilingual speakers (English & Italian) to help make advanced AI models safer. You'll apply your language fluency and cultural judgment to evaluate and strengthen how these models handle sensitive topics in Italian. No prior AI/ML experience is required — we'll train you on the workflow.

What you'll do

• Write expert-level prompts in Italian across a range of sensitive subject areas.

• Apply structured guidelines to classify prompts and conversations.

• Flag adversarial phrasings and escalation patterns, and document the reasoning behind your judgments.

What we're looking for

• Native or near-native fluency in Italian, plus business-level written English.

• A bachelor's degree, completed or in progress.

• Strong written reasoning and a high level of attention to detail.

• Sound judgment around sensitive and dual-use information.

Nice to have

• Based in Italy or the wider Western Europe region. This is a preference, not a requirement — applicants based elsewhere are welcome.

• Experience reviewing, grading, or red-teaming written or technical content.

• Background in trust and safety, content moderation, policy evaluation, or adversarial testing.

Project Timeline

• Start date: Immediate