Research Scientist, Gemini Safety

Google DeepMind

Mountain View, US
On-site
Llm post-training experience
Text-to-text modalities
Image/video/audio-to-text modalities
Google DeepMind is seeking a Research Scientist for its Gemini Safety team, focusing on enhancing the safety and fairness of AI models. The ideal candidate will have a PhD or equivalent experience in Computer Science, with significant expertise in post-training of large language models (LLMs) and a collaborative approach to research

Job Summary

  • The Gemini Safety team is accountable for the safety and fairness behavior of GDM’s latest Gemini models, applying and developing cutting-edge data and algorithmic solutions.
  • Key responsibilities include post-training LLMs, exploring data/reasoning/algorithmic solutions for safety and fairness, improving adversarial robustness, and designing evaluation protocols.
  • The team has a strong culture of support, dedication, and collaboration, working to advance the state of the art in AI for widespread public benefit and scientific discovery.

Matching Summary

Match Score: 85

Google DeepMind is seeking a Research Scientist for its Gemini Safety team, focusing on enhancing the safety and fairness of AI models. The ideal candidate will have a PhD or equivalent experience in Computer Science, with significant expertise in post-training of large language models (LLMs) and a collaborative approach to research.

Skills & Requirements

Must-have

  • LLM post-training experience
  • text-to-text modalities
  • image/video/audio-to-text modalities
  • agentic capabilities
  • adversarial robustness
  • evaluation protocols

Nice-to-have

  • reward modeling experience
  • long-range reinforcement learning
  • safety, fairness, and alignment
  • taking research to product
  • collaborating on applied research

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