Researcher, Cybersecurity Products

Details

Anthropic is looking for a Capabilities Researcher to join the team building Claude Security. The role focuses on identifying security capabilities in frontier models that are ready to build on, measuring their performance, and making them useful to customers who are not security experts. You will answer practical questions about model reliability, performance in realistic conditions, adversarial behavior, and limitations through rapid prototyping and rigorous evaluation.

You will also work with engineers to design the scaffolding, tooling, and defaults that enable strong model capabilities to perform useful security work for non-experts, remaining involved as those capabilities become part of a product.

Responsibilities

• Rapidly prototype to define the AI frontier for cybersecurity work.
• Design evaluations that measure model performance on work performed by security teams.
• Build the datasets, harnesses, and scoring systems required for evaluations.
• Engage with the cybersecurity community to help identify where AI can have the greatest impact.
• Work with engineers and researchers to operationalize promising capabilities into reliable customer-facing tools.
• Track changes in model capabilities for security and assess their implications for future products.
• Share findings that inform product direction and partner with product leadership on priorities.

Requirements

• Deep expertise in one or more security domains, such as vulnerability research, exploit development, reverse engineering, malware analysis, incident response, or offensive security.
• Experience building AI-powered tools or capabilities for security work.
• Ability to move quickly from an idea to a working prototype and discard approaches that do not hold up.
• Experience designing rigorous evaluations and interpreting results honestly.
• Strong technical writing and communication skills.
• At least 7 years of experience in security research, security engineering, or a closely related field.
• A bachelor's degree or equivalent combination of education, training, and experience.
• Education, training, or professional experience in a field relevant to the role.

Preferred Qualifications

• Published research, CTF results, CVEs, or open-source security tooling.
• Experience with model evaluation, benchmarking, or red teaming.
• Experience building agentic applications.
• Familiarity with the safety considerations of AI in security contexts.

Benefits

Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and an office space for collaboration. Anthropic expects staff to work from one of its offices at least 25% of the time, although some roles may require more office time. Anthropic sponsors visas where possible and retains an immigration lawyer to assist with visa applications.