AGI Safety & Alignment Research Scientist

Google LLC; Greater London; On-site; GBP 70,000 - 110,000; Full time

Benefits offered by this job

Equity grants

Job summary

DeepMind in London is seeking a Research Scientist for AGI Safety and Alignment to advance research on safe and aligned frontier models. You will collaborate with ASAT teams, contribute to scaling alignment techniques, and help translate research into production systems, while working with product teams to ensure safe adoption.

The role requires strong CS foundations and experience in ML research or ML engineering.

Qualifications

• Bachelor’s degree in Computer Science, a related software field, or equivalent practical experience.
• At least 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.

Skills

Research experience

Team collaboration

ML engineering

Education

Bachelor's degree in CS or related field

Job description

DeepMind in London is seeking a Research Scientist for AGI Safety and Alignment to advance research on safe and aligned frontier models. You will collaborate with ASAT teams, contribute to scaling alignment techniques, and help translate research into production systems, while working with product teams to ensure safe adoption.

The role requires strong CS foundations and experience in ML research or ML engineering.