Research Scientist, Gemini Safety and Behavior
$207k - $300k • New York, NY, USA; Mountain View, CA, USA; London, UK • Full-time
Posted 1mo ago
Job Location
New York, NY, USA; Mountain View, CA, USA; London, UK
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Research Engineer
About the job
The Alignment and Reliability division investigates and creates auditing frameworks, defensive safeguards, specialized toolsets, and autonomous agents to upgrade foundation systems. The mandate for the Research Scientist/Engineer centers on engineering novel heuristic and statistical mechanisms to elevate user-facing architectures. The operating rhythm is swift and deeply team-oriented, anchored by a collective ethos of mutual assistance, resilience, and camaraderie intervening during urgent escalations while shaping next-generation intelligence. In this role, you will be a technical contributor capable of advancing fresh investigative hypotheses from conception to live release with full lifecycle accountability, balancing experimentation with rapid incident mitigation. Our group specializes in enhancing the ethical integrity and alignment standards of machine intelligence, pioneering foundational infrastructure integrated across major downstream surfaces, including flagship consumer interfaces, developer APIs, and core search platforms.
Responsibilities
- Drive innovation and understanding of safety and security jailbreaks, delivering scalable mitigations in partnership with product areas.
- Develop red and blue teaming methods for frontier GenAI models (text-to-text, multimodal, agentic), delivering actionable insights and solutions.
- Explore data, reasoning, and algorithmic solutions to ensure Gemini Models are safe, maximally helpful, and work for everyone.
- Improve Gemini's adversarial robustness, focusing on high-stakes abuse risks in agentic settings.
- Develop and execute experimental plans to address known gaps or construct new capabilities.
Requirements
- PhD degree in Computer Science, a related field, or equivalent practical experience.
- 2 years of experience in Large Language Model safety or security.
- Experience in developing and leveraging agentic workflows around safety, behavior, and alignment.
- Experience with synthetic data generation pipelines, building evaluations and mitigations for non-verifiable tasks using methods such as LLM-as-a-judge, rubric-based rewards, etc.
- Experience taking research from concept to product.
- Experience with collaborating or leading an applied research project.
- Strong experimental taste with good judgment regarding baselines, ablations, and what is worth testing.
- Track record of publications at NeurIPS, ICLR, ICML.
Benefits
- 20% bonus target
- equity
- benefits at Google
