Radiological AI Safety Scientist

DeepMind Technologies Limited; New York (NY); On-site; USD 174,000 - 252,000; Full time

Job summary

Google DeepMind invites applications for a Radiological Subject Matter Expert (SME) in the CBRNE team within the ReDI group. The role focuses on evaluating and mitigating safety risks of frontier AI models in radiological contexts, including radiation and neutron transport modeling and detector shielding optimization.

The successful candidate will work as a Research Scientist, collaborating across interdisciplinary teams to ensure safe AI development and responsible innovation in high-stakes

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.

Responsibilities

• 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 across the domain.
• Collaborate with engineers to design mitigations that block harmful outputs without overly degrading the model's scientific utility.
• Support development and refinement of Google’s nuclear safety policy. Communicate complex risks, evaluation findings, and mitigation strategies to leadership and external stakeholders.
• Develop mathematical and computational frameworks to quantify capability thresholds, technical feasibility, and potential consequences of model uplift wherever possible.

Skills

PhD and Postdoc experience

3 years national lab/security research

Radiological/nuclear security policy

Radiation/neutron transport expertise

Education

PhD or equivalent

Tools

Python

C++

Job description

Google DeepMind invites applications for a Radiological Subject Matter Expert (SME) in the CBRNE team within the ReDI group. The role focuses on evaluating and mitigating safety risks of frontier AI models in radiological contexts, including radiation and neutron transport modeling and detector shielding optimization.

The successful candidate will work as a Research Scientist, collaborating across interdisciplinary teams to ensure safe AI development and responsible innovation in high-stakes