AI Safety & Alignment Research Scientist

DeepMind Technologies Limited

Mountain View (CA)

Presencial

USD 174.000 - 252.000

Tempo integral

14 dias+

Receba uma resposta desta empresa empregadora

Seu currículo e carta de apresentação personalizados exatamente para o que estão contratando.

Passe pelos filtros ATS

Resumo da vaga

Google DeepMind seeks a Research Scientist for the Gemini Safety team to design algorithmic solutions advancing user-facing architectures. You will bring post-training expertise to ensure outputs are aligned and production-ready, coordinating with Gemini post-training and core Product Area counterparts.

You will be a builder and shipper with end-to-end ownership, formulating mitigation frameworks and evaluations while guiding cross-functional alignment for deployment across launch surfaces.

Qualificações

  • 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.

Responsabilidades

  • 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.

Conhecimentos

Generative AI experience

Formação

PhD in Computer Science or related field

Descrição da vaga

Google DeepMind seeks a Research Scientist for the Gemini Safety team to design algorithmic solutions advancing user-facing architectures. You will bring post-training expertise to ensure outputs are aligned and production-ready, coordinating with Gemini post-training and core Product Area counterparts.

You will be a builder and shipper with end-to-end ownership, formulating mitigation frameworks and evaluations while guiding cross-functional alignment for deployment across launch surfaces.

Obtenha sua revisão de currículo grátis e confidencial.

ou arraste e solte seu arquivo aqui.

Similar jobs

Vagas similares que valem a pena comparar

Research Scientist, AI Safety & Alignment (Post-Training)
Research Scientist, AI Safety & Alignment (Post-Training)

DeepMind • Mountain View (CA)

Presencial
USD 207.000 - 300.000
Gemini Safety Research Engineer - Post-Training AI Alignment
Gemini Safety Research Engineer - Post-Training AI Alignment

DeepMind • Mountain View (CA)

Presencial
USD 174.000 - 252.000
Equity
Bonus target
Senior AI Safety and Alignment Research Scientist
Senior AI Safety and Alignment Research Scientist

Google DeepMind • Mountain View (CA)

Presencial
USD 207.000 - 300.000
Research Scientist, AI Safety & Alignment (Post-Training)
Research Scientist, AI Safety & Alignment (Post-Training)

Google LLC • Mountain View (CA)

Presencial
USD 174.000 - 252.000
Safety & Behavior Scientist for Gemini AI Systems
Safety & Behavior Scientist for Gemini AI Systems

Google LLC • New York (NY)

Presencial
USD 207.000 - 300.000
Equity
Bonus target
Research Scientist, Gemini Agent Safety Post Training, DeepMind
Research Scientist, Gemini Agent Safety Post Training, DeepMind

Google DeepMind • Mountain View (CA)

Presencial
USD 207.000 - 300.000
Research Scientist, Gemini Agent Safety, DeepMind
Research Scientist, Gemini Agent Safety, DeepMind

DeepMind Technologies Limited • Mountain View (CA)

Presencial
USD 174.000 - 252.000
Research Scientist, Gemini Agent Safety
Research Scientist, Gemini Agent Safety

Google LLC • Mountain View (CA)

Presencial
USD 174.000 - 252.000
AI-Driven Software Research Engineer
AI-Driven Software Research Engineer

Google DeepMind • Mountain View (CA)

Presencial
USD 147.000 - 210.000
Equity
Bonus target
Benefits
Research Scientist, Gemini Safety and Behavior, DeepMind
Research Scientist, Gemini Safety and Behavior, DeepMind

DeepMind Technologies Limited • New York (NY)

Presencial
USD 207.000 - 300.000