Research Scientist: AI Safety & Alignment

DeepMind Technologies Limited; Greater London; On-site; GBP 120,000 - 180,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

DeepMind Technologies Limited seeks a Research Scientist/Engineer to advance novel heuristic and statistical mechanisms for safety and alignment in flagship foundation systems. You will work in a fast-paced, team-oriented environment, contributing from conception to live release with accountability across the full lifecycle.

The role emphasizes ethical integrity, alignment standards, and scalable defenses across consumer interfaces, APIs, and core search platforms, with a broad scope for

Qualifications

• PhD in Computer Science or related field, or equivalent practical experience.
• 2 years of experience in Large Language Model safety or security.

Responsibilities

• Drive innovation and understanding of safety and security measures, delivering mitigations at scale.
• Develop red and blue teaming methods for frontier GenAI models, delivering actionable insights.
• Explore data, reasoning and algorithmic solutions to ensure model safety and usefulness.
• Improve adversarial robustness in high-stakes agentic settings.
• Develop and execute experimental plans to address known gaps or create new capabilities.

Skills

Agentic workflows

Synthetic data pipelines

Research to product

Applied research leadership

Experimental judgment

Publications in ML venues

Education

PhD in CS or related field

Job description

DeepMind Technologies Limited seeks a Research Scientist/Engineer to advance novel heuristic and statistical mechanisms for safety and alignment in flagship foundation systems. You will work in a fast-paced, team-oriented environment, contributing from conception to live release with accountability across the full lifecycle.

The role emphasizes ethical integrity, alignment standards, and scalable defenses across consumer interfaces, APIs, and core search platforms, with a broad scope for