Technical Threat Investigator, Safeguards (CBRN)

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 this role

As a Technical Threat Investigator focused on CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosives) risks with particular emphasis on biodefense, you will be responsible for detecting, investigating, and disrupting the misuse of Anthropic's AI systems for biological threats and harm on Anthropic’s threat intelligence team. This role combines deep technical investigation skills with specialized domain expertise in biodefense to protect against sophisticated threat actors who may attempt to leverage our AI technology for malicious biological applications.

You will work at the intersection of AI safety and biosecurity, conducting thorough investigations into potential misuse cases, developing novel detection techniques, and building robust defenses against emerging biological threats in the rapidly evolving landscape of AI-enabled risks.

Important context for this role: In this position you may be exposed to and engage with explicit content spanning a range of topics, including those of a sexual, violent, or psychologically disturbing nature. This role may require responding to escalations during weekends and holidays.

Responsibilities:

• Detect and investigate CBRN threats: Identify and thoroughly investigate attempts to misuse Anthropic's AI systems for developing, enhancing, or disseminating CBRNE weapons, pathogens, toxins, or other CBRNE threats to harm people, critical infrastructure, or the environment. The primary focus will be on biological and chemical harms.
• Cross-platform threat analysis: Ground investigations in real threat actor behavior, basing findings off of cross-internet and open-source research, as well as past publicly reported programs.
• Conduct technical investigations: Utilize SQL, Python, and other technical tools to analyze large datasets, trace user behavior patterns, and uncover sophisticated CBRNE threat actors across our platform.
• Create actionable intelligence: Develop detailed threat intelligence reports on biological attack vectors, vulnerabilities, and threat actor TTPs leveraging AI systems, with specific focus on biodefense implications.
• Develop biological-specific detection capabilities: Create abuse signals, tracking strategies, and detection methodologies specifically tailored to identify users attempting dual-use biological misuse, including emerging biothreat vectors and novel attack patterns.
• Collaborate with policy & enforcement teams: Work closely with policy & enforcement teams to make informed decisions about user violations related to biological threats and ensure appropriate mitigation actions.
• External stakeholder engagement: Communicate findings with external partners including government agencies, regulatory bodies, scientific organizations, and biosecurity research communities.

You may be a good fit if you:

• Have biological and chemical domain expertise: Possess deep knowledge in biosecurity, biological weapons non-proliferation, dual-use research of concern (DURC), biodefense, synthetic biology, or related biological threat domains
• Strong technical investigation skills: Demonstrated experience in technical analysis and investigations, with proficiency in SQL, Python, and data analysis tools for threat detection and user behavior analysis
• Threat intelligence or Targeting background: Experience in threat actor profiling, utilizing threat intelligence frameworks, and conducting adversarial analysis, particularly in biosecurity or related domains
• Experience with AI systems: Have hands-on experience with large language models and deep understanding of how AI technology could potentially be misused for biological threats
• Cross-functional collaboration: Excellent stakeholder management skills and ability to work effectively with diverse teams including researchers, policy experts, legal teams, and external partners
• Communication skills: Ability to present analytical work to both technical and non-technical audiences, including government stakeholders and senior leadership

Preferred qualifications:

• Advanced degree (MS or PhD) in biological sciences, biodefense, biosecurity, or related field, or equivalent professional experience
• Real world experience countering weapons of mass destruction, CBRNE, or other high risk dangerous asymmetric threats
• 3+ years of experience in biosecurity threat analysis, biological defense, or related investigative roles
• Comfortable with SQL and Python
• Experience working with government agencies or in regulated environments dealing with sensitive biological information
• Background in AI safety, machine learning security, or technology abuse investigation
• Familiarity with synthetic biology, biotechnology, or dual-use biological research
• Experience building and scaling threat detection systems or abuse monitoring programs

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.