Research Scientist, AGI Safety and Alignment, DeepMind

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

Research Scientist, AGI Safety and Alignment, DeepMind

Share Research Scientist, AGI Safety and Alignment, DeepMind

corporate_fare DeepMind place London, UK

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

Preferred qualifications:

• Experience conducting or contributing to applied research to improve the safety and alignment of frontier AI systems.
• Experience with training large models (e.g., supervised finetuning, RLHF).

About the job

The Artificial General Intelligence (AGI) Safety and Alignment Team (ASAT) aims to reduce existential and catastrophic risk from AGI and eventually Artificial Superintelligence (ASI). We research novel techniques and work with the rest of GDM and Google to apply them. We advise executive leadership on safety.

ASAT has sub-teams specializing in making future Geminis more thoroughly aligned by finding and fixing sources of misalignment and exploring alignment techniques with better generalization. Preparing for future AGI risks by simulating them today and using interpretability techniques to understand AI and solve practical problems like model forensics or evaluation (eval) awareness. Building control for GDM’s agents as defense-in-depth against potential misaligned internal deployments. Researching training techniques, like debate, for aligning superhuman AI and ways to retain, improve, and measure monitorability. Researching and implementing ways to assess the ways in which a given model might be imperfectly aligned and developing and implementing tools and AI assistance that accelerates safety research. Advising executive leadership on risks posed by AI systems via the frontier safety framework based on our threat models and evaluations. We are prioritizing hires for deep alignment, alignment stress testing, language model interpretability, agent control, and amplified oversight. We are looking to grow our team with researchers and engineers. Depending on your background, we have opportunities available as both Research Scientists and Software Engineers.

Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority. We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.

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.

Google is proud to be an equal opportunity and affirmative action employer. We are committed to building a workforce that is representative of the users we serve, creating a culture of belonging, and providing an equal employment opportunity regardless of race, creed, color, religion, gender, sexual orientation, gender identity/expression, national origin, disability, age, genetic information, veteran status, marital status, pregnancy or related condition (including breastfeeding), expecting or parents-to-be, criminal histories consistent with legal requirements, or any other basis protected by law. See also Google's EEO Policy , Know your rights: workplace discrimination is illegal , Belonging at Google , and How we hire .

Google is a global company and, in order to facilitate efficient collaboration and communication globally, English proficiency is a requirement for all roles unless stated otherwise in the job posting.

Equity is granted exclusively and discretionarily by Alphabet Inc. on the basis of an agreement concluded between you and Alphabet Inc. Alphabet Inc. is your sole contractual partner with respect to equity grants. GSU grants are not guaranteed, are discretionary, are subject to approval by the Alphabet Inc. board of directors or its delegate, the terms of the relevant Alphabet Inc. stock plan, and your grant agreement. They have no impact on statutory payments. Current or past grants do not confer an acquired right.