AGI Safety & Alignment Research Engineer

Google DeepMind's AGI Safety and Alignment Team (ASAT) seeks researchers and engineers to advance alignment techniques for frontier models. You will contribute to safety research, build robust control systems, and collaborate with product teams to ensure safe and effective deployment across platforms.

The team focuses on misalignment sources, safety frameworks, and evaluating risk with executives, shaping research that reduces existential AI risks while enabling safe innovations for billions of