Research Scientist, Gemini Safety

Google DeepMind

Zurich, Switzerland
On-site
Llm post-training experience
Text-to-text modalities
Image/video/audio-to-text modalities
The Gemini Safety team is accountable for the safety and fairness behavior of GDM’s latest Gemini models

Job Summary

  • The Gemini Safety team is accountable for the safety and fairness behavior of GDM’s latest Gemini models.
  • The role of the Research Scientist will be to apply and develop data and algorithmic cutting edge solutions to advance GDM’s latest user-facing models.
  • The team has a strong culture of support, dedication and collaboration.

Matching Summary

The Gemini Safety team is accountable for the safety and fairness behavior of GDM’s latest Gemini models.

Skills & Requirements

Must-have

  • LLM post-training experience
  • text-to-text modalities
  • image/video/audio-to-text modalities
  • agentic capabilities
  • adversarial robustness
  • high-stakes abuse risks

Nice-to-have

  • reward modeling for LLMs
  • reinforcement learning for LLMs
  • long-range reinforcement learning
  • safety, fairness, and alignment
  • strong experimental taste
  • collaborating applied research project

Key Requirements

  • PhD in Computer Science or related field
  • Equivalent practical experience
  • Significant LLM post-training experience

Work Rights

Not specified

Tailored Resume

Cover Letter