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

Google LLC; Mountain View (CA); Presencial; USD 174 000 - 252 000; Tempo integral

Resumo da oferta

Google DeepMind is seeking a Research Scientist for Gemini Agent Safety Post Training in Mountain View. You will develop algorithmic solutions to advance user-facing architectures and ensure outputs are aligned and production-ready.

The role emphasizes post-training expertise, cross-functional coordination, and end-to-end ownership of mitigation frameworks. You will drive research concepts to product realization with a strong engineering and experimental track record, contributing to ambitious

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 safety protocols to identify gaps in model behavior across Gemini and GenAI models.
• Feed safety insights back into the post-training process to improve in-model and out-of-model protection.
• Explore modeling and alignment techniques to address safety and alignment challenges under launch timelines.
• Collaborate with post-training, evaluation, and product teams to align incentives and influence safety decisions.

Conhecimentos

Generative AI

NLP

Agent-based systems

Formação académica

PhD in Computer Science or related field, or equivalent practical experience

Descrição da oferta de emprego

Google DeepMind is seeking a Research Scientist for Gemini Agent Safety Post Training in Mountain View. You will develop algorithmic solutions to advance user-facing architectures and ensure outputs are aligned and production-ready.

The role emphasizes post-training expertise, cross-functional coordination, and end-to-end ownership of mitigation frameworks. You will drive research concepts to product realization with a strong engineering and experimental track record, contributing to ambitious