Research Scientist, Frontier, Zurich

Snapshot

At Google DeepMind, we foster an environment where ambitious, long-term research flourishes. Our team is tackling one of the hardest problems in modern AI: Post-training Frontier models. Unlike smaller models that can rely on distillation, our frontier models require novel training signals to advance the state of the art. We are defining the horizontal recipes—from revamping RL prompts to advancing Reward Models (RM) —that allow these models to think better, reason deeper, and align more closely with human intent. We believe that mastering the feedback loop between user signals and model behavior is the key to breaking through current performance plateaus.

About Us

Artificial Intelligence could be one of humanity's most useful inventions. At Google DeepMind, we're a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence. We use our technologies for widespr...