Research Scientist - AI Alignment & AGI Safety

DeepMind Technologies Limited; Greater London; On-site; GBP 85,000 - 120,000; Full time

Job summary

DeepMind Technologies Limited is seeking researchers and software engineers to join the Artificial General Intelligence Safety and Alignment Team (ASAT). The role focuses on advancing alignment, safety research, and scalable AGI control concepts across frontier models.

You will collaborate with cross-disciplinary teams to develop novel safety techniques, study alignment failures, and contribute to interpretability methods while shaping responsible AI deployment strategies at scale.

Qualifications

• Bachelor's degree in CS or related field, or equivalent practical experience.
• 3 years of experience in software development, ML engineering, or ML research.
• Experience working with research teams.

Responsibilities

• Research new alignment methods, study alignment failures, and apply AGI-scalable alignment techniques to frontier models.
• Develop AGI control systems and implement them in production.
• Research interpretability techniques to understand what AI systems are thinking.
• Work with product teams to ensure that our research is correctly adopted.

Education

Bachelor's degree in Computer Science, a related Software Engineering field, or equivalent practical experience

Job description

DeepMind Technologies Limited is seeking researchers and software engineers to join the Artificial General Intelligence Safety and Alignment Team (ASAT). The role focuses on advancing alignment, safety research, and scalable AGI control concepts across frontier models.

You will collaborate with cross-disciplinary teams to develop novel safety techniques, study alignment failures, and contribute to interpretability methods while shaping responsible AI deployment strategies at scale.