Senior GenAI Safety Researcher: Frontier Risk & Red-Teaming

Jobgether

Stati Uniti

In loco

USD 140.000 - 220.000

Tempo pieno

22 ore fa

Candidati tra i primi

Una candidatura completa in un minuto

Curriculum e lettera di presentazione personalizzati, pronti da inviare.

Supera i filtri ATS

Descrizione del lavoro

Jobgether is seeking a Senior GenAI Safety Researcher: Frontier Risk to join a partner-led initiative in the United States. You will lead research execution on frontier AI safety, focusing on CBRNE and cybersecurity risks, and serve as the bridge between client partners and internal researchers.

You will coordinate multi-disciplinary teams, drive rigorous evaluation methodologies, and present defensible risk assessments to safety leadership.

Competenze

2–4 years of experience in AI safety, red-teaming, CBRNE risk, cybersecurity, or cyber threat intelligence.
Proven ability to lead complex technical projects and coordinate specialized experts toward demanding delivery deadlines.
Excellent written and verbal communication skills, able to convey high-stakes risks to engineers and executives.

Mansioni

Lead development and execution of red-teaming datasets, evaluation protocols, and risk reports.
Establish QA checkpoints across base-model evaluations, guardrails, and agentic workflows for text, vision, and audio modalities.
Coordinate specialized research teams and manage delivery timelines.
Serve as the primary analytical lead during client engagements, presenting threat models and mitigation recommendations.
Translate complex findings into actionable guidance for client engineering teams and safety leadership.