Vai al contenuto
AI.info

jobs

Research Scientist, Gemini Agent Safety Post Training, DeepMind

The Gemini Safety team is accountable for the standards of GDM’s flagship releases. In this role, you will develop algorithmic solutions to advance user-facing architectures.

In inglese

Company
Google
Location
Mountain View, CA, USA
Status
Closed
Posted
2026-11-11 11:38 UTC

Google DeepMind seeks a Research Scientist for its Gemini Safety team in Mountain View. The role focuses on finding safety gaps in Gemini and other generative models, then improving post-training so model behavior is safer and production-ready. Work includes designing evaluation protocols, applying alignment and modeling techniques under launch deadlines, and scaling supervised fine-tuning and reinforcement learning. The posting asks for a PhD or equivalent experience, three years of research leadership, and peer-reviewed publications, with preferred experience in AI safety, reward modeling, agents, and ML infrastructure. On-site, full-time.

Original job posting