info_outline
X Note: By applying to this position you will have an opportunity to share your preferred working location from the following:
Mountain View, CA, USA; New York, NY, USA.
Minimum qualifications: - PhD in chemistry, or equivalent practical experience.
- 7 years of experience with national, or international chemical security organisations (e.g., OPCW, national laboratories, or AI Safety Institutes).
- Experience working with national security or defense organizations on technical chemical matters.
- Experience working with LLMs in your daily workflows, and applying LLMs to scientific problems.
Preferred qualifications: - Experience designing novel science evaluations, red-teaming protocols, or threat-analysis frameworks for emerging technologies.
- Understanding of the training, operating principles, and mitigation strategies of Large Language Models (LLMs) used to prevent the proliferation of dual-use scientific information.
- Understanding of model evaluation methodologies for determining the frontier risks of modern AI models.
- Active, ongoing engagement and established credibility with national, or international chemical security organizations (e.g., OPCW, National Academies, national laboratories, or AI Safety Institutes).
About the jobIn this role, you will serve as the Lead Scientist for a team of chemists, joining a wider group of Subject Matter Experts (SMEs) and Research Scientists within Google's Chemical, Biological, Radiological, Nuclear and Explosives (CBRNE) team. Together, you will ensure that as Gemini's scientific capabilities advance, it does not become a tool for catastrophic harm.
You will apply your knowledge of dual-use chemistry to lead policy development, direct the design of evaluations aimed at understanding the maximum capabilities of our AI models, and shape mitigation strategies to ensure our models are safe for release. You will also serve as DeepMind's primary scientific representative on chemical security to senior internal leadership and external government and international stakeholders.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $262000 - $364000 (USD) 25% bonus target equity benefits
Learn more about benefits at Google .
Responsibilities - Lead the design and execution of all chemical evaluations to understand the maximum agentic capabilities of our AI models.
- Provide recommendations for implementing mitigations to ensure the chemical safety of our models, while minimizing the impact on legitimate science.
- Partner closely with the team of chemists, Research Scientists, Engineers, and ethics experts to embed chemical safety protocols directly into the model development lifecycle.
- Communicate technical results and commentary to audiences with a range of expertise, up to senior internal and external decision-makers.
- Shape DeepMind's broader chemical security mitigation strategies, ensuring safety guardrails protect against genuine misuse without adversely affecting legitimate scientific research.
