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 virology or equivalent practical experience.
- 2 years of postdoctoral or clinical experience spanning pathogenic viruses, bacteria, or agriculture.
- 2 years of experience applying biosecurity principles to evaluate the intersection of microbiology and AI safety, including Large Language Model (LLM) risk assessments.
- Experience identifying and documenting misuse scenarios for emerging technologies.
- Experience delivering technical presentations or reports, and translating data for cross-functional stakeholders.
Preferred qualifications: - Experience in clinical wet lab virology and working in BSL-2 labs (or higher).
- Experience in using command line tools and coding.
- Knowledge of the issues with Dual Use Biology.
- Knowledge of issues of biological weapons, potential mitigations and awareness of relevant stakeholders.
- Understanding of Safety Frameworks in AI. Knowledge of the Biological Weapons Convention. An interest in the ethics and safety of AI systems, and in AI policy.
- Actively leveraged AI tools to accelerate research pipelines or safety benchmarks by a measurable margin.
About the jobAs a part of the Responsible Development and Innovation team (ReDI) at DeepMind, you will be a virologist with extensive wet lab experience, focused on biology evaluations and mitigations of large language models (LLMs).
In this role, you will develop and maintain evaluations that enable decision-makers to ensure model releases are safe and responsible, along with the infrastructure that supports them.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $174000 - $253000 (USD) 15% bonus target equity benefits
Learn more about benefits at Google .
Responsibilities - Design, develop and execute biology evaluations to test the safety of AI models.
- Drive the development and delivery of harm frameworks and mitigation strategies.
- Communicate results to relevant teams and decision-makers.
- Collaborate with experts in various fields of science, AI ethics, policy and safety.
