Research Scientist - AI Safety & Harmful Manipulation

DeepMind Technologies Limited; Greater London; Hybrid; GBP 129,000 - 187,000; Full time

Job summary

Google DeepMind is seeking a Senior Research Scientist for the Responsible Development and Innovation team to study Harmful Manipulation risks in AI systems. You will design evaluations, investigate model-user interactions, publish methodologies, and support governance decisions while collaborating with cross-functional teams.

The role emphasizes bridging research and practical deployments, contributing to safer AI products used by billions and shaping policy discussions with external

Qualifications

• PhD degree in a related field or equivalent practical experience.
• Experience designing evaluations or studies to investigate AI manipulation, persuasion, or related social phenomena.

Responsibilities

• Design and implement evaluations identifying Harmful Manipulation-related capabilities and risks; publish on novel methodologies and insights.
• Collaborate across teams to carry out risk assessments, ensuring deployment safeguards are adequate for high-capability models.
• Support mitigation efforts by working with evaluation and mitigation teams and providing actionable insights.
• Engage with external researchers and stakeholders, including government bodies and safety institutes.

Skills

Evaluation design

Research design

Education

PhD or equivalent in related field

Job description

Google DeepMind is seeking a Senior Research Scientist for the Responsible Development and Innovation team to study Harmful Manipulation risks in AI systems. You will design evaluations, investigate model-user interactions, publish methodologies, and support governance decisions while collaborating with cross-functional teams.

The role emphasizes bridging research and practical deployments, contributing to safer AI products used by billions and shaping policy discussions with external