PhD and Postdoctoral research experience in Particle Physics, Plasma Physics, Nuclear Engineering, or related fields.
3 years of research experience with US national laboratories or security initiatives.
Expertise in radiological/nuclear security, safeguards, nonproliferation, and threat reduction.
Proficient in radiation/neutron transport, reactor monitoring, and detection mechanics.
Experience with machine learning applications in radiation detection and nuclear event reconstruction.
Responsibilities
Construct threat models focusing on vulnerabilities and threat scenarios related to nuclear weapons development.
Create evaluation datasets to maximize model capabilities against malicious actors.
Collaborate with engineers to design effective mitigations that maintain scientific utility.
Support the development of Google's nuclear safety policy and communicate findings to stakeholders.
Develop frameworks to quantify technical feasibility and potential consequences of model uplift.
Benefits
Comprehensive health and wellness programs.
Generous paid time off and holidays.
Retirement savings plan with company match.
Opportunities for professional development and training.
Collaborative and innovative work environment.
Full Job Description
Minimum qualifications:
PhD and Postdoctoral research experience in Particle Physics, Plasma Physics, Nuclear Engineering, or a related field.
3 years of experience in research with US national laboratories or security initiatives (e.g., IAEA, NNSA, DARPA, or academic consortia).
Experience in research or policy in radiological/nuclear security, safeguards, nonproliferation, material control, or threat reduction.
Experience in radiation/neutron transport, reactor monitoring, detection, dosimetry, shielding defeat, and RDD/RED mechanics.
Preferred qualifications:
Experience applying ML to radiation detection, detector calibration, or nuclear/particle event reconstruction.
Experience in AI safety, evaluations, red-teaming, or applied AI research in lab, academic, or industry settings.
Experience in data analysis, scientific computing (e.g., Python or C ), and simulation in neutron/radiation transport, detector response, or plume dispersion.
Experience using AI models/agents to enhance capabilities and lower technical barriers.
Ability to design evaluations and mitigations that are demonstrably unclassified and non-export controlled by developing dual use science proxies for weapons topics. Highly collaborative, comfortable with peer review, and committed to respectful teamwork.
About the job Google invites applications from highly qualified physicists and nuclear engineers for the position of Radiological Subject Matter Expert (SME) in the CBRNE team within the Responsible Development and Innovation (ReDI) team. The successful applicant will be hired for a Research Scientist position serving as a technical expert evaluating and mitigating safety risks of frontier AI models (primarily but not limited to LLMs) in the radiological domain; specifically, model assistance in radiation and neutron transport modeling, radiation detector defeat and shielding optimization, reactor operations and monitoring, and radiological source managing in a demonstrably unclassified and non-export controlled manner.
Construct threat models prioritizing vulnerabilities, threat actors, and scenarios related to fission, fusion, thermonuclear weapons development, and high-energy-density dual-use regimes.
Create evaluation datasets of complex physics and nuclear engineering prompts to elicit the maximum capability of the model to determine how to uplift malicious actors (e.g., revealing tacit knowledge, novel procedures, time/cost reduction, detectability reduction) across the domain.
Collaborate with engineers to design mitigations that block harmful outputs without overly degrading the model's scientific utility. Similar to writing capability evaluations, this requires a deep understanding of dual-use science.
Support development and refinement of Google's nuclear safety policy. Communicate complex risks, evaluation findings, and mitigation strategies to leadership and technical/non-technical external stakeholders.
Develop mathematical and computational frameworks to quantify capability thresholds, technical feasibility, and potential consequences of model uplift wherever possible.
About Google
Google is a multinational technology company that specializes in Internet-related services and products. These include online advertising technologies, search engine, cloud computing, software, and hardware. Google was founded in 1998 by Larry Page and Sergey Brin while they were Ph.D. students at Stanford University. The company has grown tremendously since then and has become one of the most valuable companies in the world. Google's mission is to organize the world's information and make it universally accessible and useful.
