1 day ago
London, United KingdomSenior
Responsibilities
- Build novel safeguards and test them through automated and manual red teaming while measuring impacts on legitimate scientific research.
- Design, build, and operate evaluations for chemical, biological, radiological, nuclear, and explosives risks in frontier and agentic AI systems.
- Architect reliability for key systems, including safeguards and incident response.
- Partner with scientific experts to convert expert judgment into datasets and automated graders while managing sensitive data under strict security controls.
- Communicate results, uncertainty, and negative findings to technical staff and leadership.
Requirements
- Bachelor’s degree or equivalent practical experience in a management, scientific, technical, or engineering field.
- Eight years of experience writing code in a shared, version-controlled codebase with other contributors, including research software.
- Three years of experience training, fine-tuning, or evaluating machine learning models.
- Preferred: master’s degree or PhD in chemistry, physics, chemical or nuclear engineering, biology, computational science, or a related field.
- Preferred: experience building classifiers or evaluation infrastructure for large language models and applying statistics to machine learning evaluation.
- Preferred: production software experience including monitoring, on-call, or incident response.
- Preferred: experience in CBRNE security, export control, red teaming, security research, or abuse prevention.
Categories
About Google
Google builds consumer and enterprise software and services including Search, Android, YouTube, Chrome, Maps, Gmail, and Google Cloud. Its business model centers on digital advertising and paid cloud, software, and hardware offerings (e.g., Pixel and Nest) for consumers, developers, and organizations. Founded in 1998 and headquartered in Mountain View, California, Google operates globally as a subsidiary of Alphabet Inc.