Research Engineer, AGI Safety and Alignment, DeepMind

Company: Hackajob Ltd
Apply for the Research Engineer, AGI Safety and Alignment, DeepMind
Location:
Job Description:

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 specialising in making future Geminis more thoroughly aligned by findin…

WHJS1_UKTJ

…

Posted: September 24th, 2026