Safety & Behavior Scientist for Gemini AI Systems

Google; New York (NY); On-site; USD 207,000 - 300,000; Full time

Benefits offered by this job

Equity

Bonus target

Job summary

Google DeepMind in the Gemini Safety and Behavior group seeks a Research Scientist to advance safety and alignment for Gemini models. You will contribute across research and live releases, working with interdisciplinary teams to balance experimentation with rapid incident response.

The role focuses on auditing frameworks, adversarial testing, and scalable mitigations, reporting to the Alignment and Reliability division. A PhD and 2+ years in LLM safety are preferred.

Qualifications

• PhD in CS or related field, or equivalent practical experience.
• 2+ years of experience in Large Language Model safety or security.
• Publications in top venues are a plus.

Responsibilities

• Drive innovation and understanding of safety and security jailbreaks, owning the problem and delivering mitigations which can be deployed at scale in partnership with product areas.
• Develop red and blue teaming methods for frontier GenAI models spanning text-to-text, multimodal, and agentic capabilities, delivering actionable insights and solutions.
• Explore data, reasoning and algorithmic solutions to make sure Gemini Models are safe, maximally helpful, and work for everyone.
• Improve Gemini's adversarial with a focus on high-stakes abuse risks in agentic settings.
• Develop and execute experimental plans to address known gaps, or construct entirely new capabilities.

Skills

Agentic workflows

Safety and alignment

LLM safety experience

Red/blue teaming

Experimentation mindset

Publications (NeurIPS/ICLR/ICML)

Education

PhD in Computer Science or related field

Equivalent practical experience

2+ years LLM safety experience

Tools

GenAI evaluation pipelines

Synthetic data generation

Job description

Google DeepMind in the Gemini Safety and Behavior group seeks a Research Scientist to advance safety and alignment for Gemini models. You will contribute across research and live releases, working with interdisciplinary teams to balance experimentation with rapid incident response.

The role focuses on auditing frameworks, adversarial testing, and scalable mitigations, reporting to the Alignment and Reliability division. A PhD and 2+ years in LLM safety are preferred.