Research Scientist, Harmful Manipulation & AI Safety

Google LLC; Greater London; Hybrid; GBP 130,000 - 188,000; Full time

Job summary

DeepMind is seeking a Research Scientist in the Harmful Manipulation domain within the ReDI team. You will research emerging risks in harmful manipulation, develop evaluations, and publish methodologies to impact model development and governance. The role bridges research and practice across global teams and interacts with external stakeholders.

The role emphasizes safety, ethics, and collaboration with cross-functional teams to inform mitigation strategies and governance decisions.

Qualifications

• Track record of leading projects in research settings.
• Publications in high impact domain-relevant conferences or journals.
• Ability to leverage AI tools to build and accelerate research pipelines or safety benchmarks.
• Commitment to translating research insights into practical applications and working with cross-functional teams.

Responsibilities

• Partner cross-functionally to design and implement evaluations identifying Harmful Manipulation capabilities and risks.
• Publish on novel methodologies and capabilities insights.
• Collaborate across teams to carry out holistic risk assessments, including deployment safeguards.
• Engage with external research communities and stakeholders, including governmental entities and safety institutes.

Skills

Project leadership

Publications

AI tooling

Cross-functional collaboration

Job description

DeepMind is seeking a Research Scientist in the Harmful Manipulation domain within the ReDI team. You will research emerging risks in harmful manipulation, develop evaluations, and publish methodologies to impact model development and governance. The role bridges research and practice across global teams and interacts with external stakeholders.

The role emphasizes safety, ethics, and collaboration with cross-functional teams to inform mitigation strategies and governance decisions.