Anthropic

About Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

About the Team

Safeguards, Dangerous Asymmetric Harms is a team responsible for developing comprehensive safety systems and policy boundaries across CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive), Cyber, and Dangerous Asymmetric Advanced Technologies—addressing threats from everyday trust and safety risks to catastrophic AI scenarios. We blend domain expertise in CBRNE and Cyber with ML engineering to create classifiers, evaluation infrastructure, threat models, and conduct RL experiments. The team also performs AI capability uplift testing through partnerships with government laboratories and national security agencies, leveraging real-world cross-functional experience.

We are looking for a Research Scientist, CBRN (Rad/Nuke), ML, who can execute rapidly, maintain high throughput, and bring a strong builder mindset to solving complex problems. The ideal candidate will combine deep nuclear/radiological domain expertise with advanced ML capabilities to build systems that evaluate and prevent dangerous capability development. You'll be designing novel approaches to detect threats spanning from nuclear proliferation to AI-enabled radiological risks, requiring both technical sophistication and strategic thinking.

This role primarily focuses on building advanced ML systems for Nuclear and Radiological threat detection. You will use your deep technical expertise in nuclear security to inform ML solutions that prevent real-world catastrophic harm.

Responsibilities

• Apply ML/AI research to build evaluation systems for nuclear and radiological safety, with focus on proliferation detection and threat assessment
• Develop novel AI techniques to detect and prevent nuclear weapons development, including capabilities-based analysis and investment optimization
• Design and train specialized AI models for nuclear material detection, leveraging sensor data, technical signatures, and open-source intelligence
• Research and implement state-of-the-art ML approaches for identifying illicit nuclear activities and proliferation networks
• Build systems that detect nuclear technology transfers and prevent proliferation through advanced pattern recognition
• Create and implement technical systems for monitoring nuclear fuel cycle activities and detecting anomalies
• Develop classifiers that can distinguish between civilian nuclear programs and weapons development
• Build sophisticated evaluation infrastructure for measuring AI capability uplift in nuclear domains
• Design adversarial testing frameworks that probe model capabilities in nuclear security contexts
• Integrate multi-source intelligence data with ML training pipelines to improve detection accuracy
• Develop and maintain nuclear threat datasets and benchmarks while ensuring appropriate classification handling
• Create tools that allow nuclear security experts to quickly develop and deploy new detection evaluations
• Write production-quality Python code for high-throughput nuclear data processing and evaluation systems
• Contribute to nuclear risk assessments that directly inform AI model release decisions and policy development
• Work cross-functionally with nuclear policy experts, national laboratory researchers, and ML engineering teams
• Apply capability-based investment frameworks to optimize nuclear detection R&D portfolios

You may be a good fit if you

• Have deep domain expertise in nuclear physics, nuclear engineering, or nuclear security
• Possess experience with nuclear weapons effects, nuclear fuel cycles, or radiological detection systems
• Have worked with nuclear threat assessment, proliferation detection, or nuclear security policy development
• Demonstrate experience with capability-based investment planning for nuclear security programs
• Have familiarity with NNSA programs, particularly in proliferation detection and R&D
• Possess experience with nuclear detection technologies and sensor systems
• Can bridge technical nuclear knowledge with ML/AI applications for security purposes
• Have experience managing large-scale nuclear security programs or R&D portfolios
• Understand the intersection of emerging technologies and nuclear proliferation risks
• Possess strong foundation in both nuclear physics/engineering and modern ML frameworks
• Have experience translating complex technical nuclear findings into strategic recommendations
• Demonstrate ability to work with classified information and maintain appropriate security protocols
• Show experience with government nuclear security programs or military CWMD operations
• Can operate effectively in interagency environments while maintaining program focus
• Have led or contributed to nuclear security R&D initiatives

Do not rule yourself out if you do not fit every qualification - we recognize that the intersection of nuclear security and ML for threat detection is a rare combination. If you have deep expertise in nuclear threats and are eager to apply ML to prevent catastrophic risks, please consider applying.

What makes this role unique

• Strategic impact: Your work will directly prevent nuclear proliferation and shape global nuclear security architecture
• Unique technical intersection: Combine cutting-edge ML with deep nuclear domain expertise in unprecedented ways
• National security influence: Your technical assessments will directly inform nuclear deterrence and counter-proliferation strategies
• Novel problem space: Design evaluations for AI-enabled nuclear capabilities that could fundamentally change strategic stability
• Interagency leadership: Apply military and government experience to coordinate across national laboratories, NNSA, and DoD
• Investment optimization: Use capability-based frameworks to maximize impact of limited nuclear security resources
• Classification challenges: Navigate the unique ML challenges of working with highly classified nuclear data

The expected salary range for this position is:

Annual Salary:

$280,000—$340,000 USD

Logistics

Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience.

Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.

Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.

How we're different

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.

Come work with us!

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues.