← All roles

Research Scientist, Gemini Agent Safety Post Training, DeepMind

Google· DeepMind
Apply on company site
Mountain View, CA, USA$174k - $252knot specifiedPosted 2w ago

About the role

Research Scientist role focused on developing algorithmic solutions to advance user-facing architectures for Gemini and GenAI safety post-training. Requires LLM post-training expertise to ensure outputs are aligned and production-ready, with end-to-end ownership, cross-functional collaboration, and emphasis on safety and ethics.

Responsibilities

  • Design, implement, and maintain high-quality protocols to identify safety gaps in model behavior across all Gemini and GenAI models, and feed these insights back into the post-training process to continuously improve both in-model and out-of-model protection.
  • Explore, adapt, and apply innovative modeling and alignment techniques to solve real-world safety and alignment challenges under tight launch timelines.
  • Drive innovation in model optimization, advancing the application of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) techniques at massive scale.
  • Partner closely with post-training, evaluation, and product teams to align incentives, close safety gaps, and influence safety decisions without direct authority.

Qualifications

  • PhD in Computer Science, a related field, or equivalent practical experience.
  • 1 year experience with Generative AI, Large Language Models, natural language processing, or Agent-based systems.

Skills

Required:Generative AI
Nice to have:AI safetyMachine Learning infrastructureReward modeling, RL for LLMs, instruction tuningResearch to product realizationPublications

Benefits

  • Learn more about benefits at Google (link provided)
Last updated Oct 23, 2026. Interested? Apply on the company site.

About Google

Google Search homepage

llmtext-to-speechvoice-ai-stack

More open roles at Google