Research Scientist: Harmful Manipulation & AI Safety

Google LLC; New York (NY); In loco; USD 174.000 - 252.000; Tempo pieno

Descrizione del lavoro

Google DeepMind in the United States is seeking a Research Scientist to advance Harmful Manipulation research within the Responsible Development and Innovation team. You will design evaluations, probe AI-driven user interactions, and publish novel methodologies.

You will collaborate with cross-functional partners, inform mitigation and governance decisions, and contribute to practical safeguards for high‑capability models, balancing safety with innovation.

Competenze

• PhD required or equivalent practical experience.
• Experience designing evaluations or studies on tech manipulation, persuasion, or social phenomena.

Mansioni

• Partner cross-functionally to design and implement evaluations identifying Harmful Manipulation-related capabilities and publish methodologies.
• Collaborate across teams for holistic risk assessments and deployment safeguards adequacy.
• Assist mitigation efforts and share actionable insights across Google.
• Engage with external research communities and stakeholders including government and academic partners.

Conoscenze

Evaluation design

AI safety

Cross-functional collaboration

Research communication

Publications

Project leadership

Formazione

PhD in Psychology, Political Science, Computational Social Science, Computer Science, or related field

Descrizione del lavoro

Google DeepMind in the United States is seeking a Research Scientist to advance Harmful Manipulation research within the Responsible Development and Innovation team. You will design evaluations, probe AI-driven user interactions, and publish novel methodologies.

You will collaborate with cross-functional partners, inform mitigation and governance decisions, and contribute to practical safeguards for high‑capability models, balancing safety with innovation.