Staff Research Scientist in Rl, Deepmind

Google Google · Big Tech · New York, NY +2

Research Scientist at DeepMind focused on Reinforcement Learning and AI alignment for Gemini models, developing next-generation post-training algorithms and theoretical frameworks.

What you'd actually do

  1. Lead ambitious, long-term research projects aimed at achieving fundamental breakthroughs in Reinforcement Learning and AI alignment.
  2. Develop the next generation of post training algorithms.
  3. Invent, develop, and rigorously test novel algorithms and theoretical frameworks that advance current capabilities in controlling and steering large-scale models.
  4. Partner with teams to transform your scientific discoveries into real-world impact on a global scale via the Gemini models.

Skills

Required

  • PhD in Computer Science or related field
  • 4 years of experience with research agendas across multiple teams or projects
  • 4 years of experience in Reinforcement Learning (RL)
  • One or more scientific publication submission(s) for conferences, journals, or public repositories

Nice to have

  • 2 years of experience in coding and leading multiple research efforts and influencing research direction

What the JD emphasized

  • Reinforcement Learning
  • AI alignment
  • post training algorithms
  • controlling and steering large-scale models
  • scientific publication submission(s)

Other signals

  • Reinforcement Learning
  • AI alignment
  • Gemini models
  • post training algorithms