Research Scientist - AI Safety & Harmful Manipulation

DeepMind Technologies Limited; New York (NY); Hybrid; USD 174,000 - 252,000; Full time

Job summary

DeepMind Technologies Limited in the United States is seeking a researcher for the Responsible Development and Innovation team to study Harmful Manipulation risks in AI systems.

You will design evaluations, collaborate across teams on risk assessments, and help inform safeguards, governance, and deployment decisions while engaging with external researchers and policymakers. This role offers opportunities to publish methodologies and contribute to responsible AI practice.

Qualifications

• PhD degree in Psychology, Political Science, Computational Social Science, Computer Science, a related field, or equivalent practical experience.
• Experience designing evaluations or studies to investigate the intersections of technology and manipulation, persuasion, social engineering, or related social phenomena.

Responsibilities

• Design and implement evaluations identifying Harmful Manipulation-related capabilities and risks; publish on novel methodologies and capabilities insights
• Collaborate across teams to carry out holistic risk assessments, including determining if deployment safeguards are adequate for high-capability models
• Work across evaluation and mitigation teams to assist mitigation efforts, while collaborating across Google to provide novel and actionable insights
• Engage with external research community and stakeholders, including governmental entities, national safety institutes, third-party organisations (including the Frontier Model Forum), external subject matter experts, and academic communities.

Skills

Evaluation design

Education

PhD or equivalent practical experience

Job description

DeepMind Technologies Limited in the United States is seeking a researcher for the Responsible Development and Innovation team to study Harmful Manipulation risks in AI systems.

You will design evaluations, collaborate across teams on risk assessments, and help inform safeguards, governance, and deployment decisions while engaging with external researchers and policymakers. This role offers opportunities to publish methodologies and contribute to responsible AI practice.