AGI Safety & Alignment Research Engineer

Google

Greater London

On-site

GBP 160,000 - 200,000

Full time

9 days ago

Application generator

Don’t send a generic resume — generate a resume and cover letter tailored to this exact role.

Get past ATS filters

Job summary

Google DeepMind ASAT is seeking researchers and software engineers to advance AGI safety and alignment. The team studies alignment failures, develops robust control systems, and collaborates with product teams to deploy safe AI features.

We value contributions to interpretable AI and scalable safety strategies, with opportunities across research and engineering roles. This is a high-impact position, offering a competitive UK salary and collaboration with leading minds in the field.

Qualifications

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

Responsibilities

Research new alignment methods and apply scalable alignment techniques to frontier models.
Develop adversarially robust AGI control systems and productionize them.
Investigate interpretability techniques to understand AI system behavior.
Collaborate with product teams to translate research into features.
Explore methods to reduce existential and catastrophic risk from AGI and ASI.
Advise leadership on AI safety risks and mitigation strategies.
Identify misalignment sources and build tools that accelerate safety research.