Red Team Engineer • Staff

Who you are

You have a strong background in security engineering, with experience in adversarial testing and vulnerability assessment — you've worked on uncovering vulnerabilities in complex systems and understand the unique challenges posed by advanced AI capabilities. Your expertise in Python allows you to develop creative attack scenarios and implement novel testing approaches effectively.

You are familiar with the full spectrum of potential abuse in AI systems, from account manipulation to payment fraud — you have a keen eye for detail and can simulate sophisticated threat actors who chain multiple attack vectors to achieve their objectives. Your understanding of traditional security practices complements your innovative approach to AI safety.

You thrive in collaborative environments and enjoy working with cross-functional teams — your communication skills enable you to articulate complex security concepts to both technical and non-technical stakeholders. You are passionate about the implications of AI safety and are committed to ensuring that AI systems are beneficial for society.

Desirable

Experience with cloud platforms like AWS is a plus, as is familiarity with machine learning frameworks — you understand how to leverage these technologies to enhance security measures. A background in research or a related field can also be beneficial, as it allows you to stay ahead of emerging threats and vulnerabilities.

What you'll do

In this role, you will conduct comprehensive adversarial testing across Anthropic’s product surfaces — you'll develop creative attack scenarios that combine multiple exploitation techniques to uncover vulnerabilities before they can be exploited by malicious actors. Your work will involve researching and implementing novel testing approaches for emerging capabilities, including agent systems and new interaction paradigms.

You will design and execute 'full kill chain' attacks that emulate sophisticated threat actors — your ability to think like an adversary will be crucial in identifying potential risks and vulnerabilities in our AI systems. You will collaborate closely with engineers and researchers to ensure that our products are safe and reliable.

Your responsibilities will also include documenting your findings and providing actionable recommendations to improve our security posture — you will play a key role in shaping the security strategies of our AI systems. You will stay updated on the latest trends in AI safety and security, ensuring that Anthropic remains at the forefront of this critical field.

What we offer

Anthropic is a public benefit corporation with a mission to create reliable and interpretable AI systems — we offer competitive compensation and benefits, including optional equity donation matching and generous vacation and parental leave. Our flexible working hours allow you to balance your professional and personal life effectively.

You will have the opportunity to work in a lovely office space in San Francisco, collaborating with a diverse team of researchers, engineers, and policy experts — we believe that a collaborative environment fosters innovation and creativity. Join us in our mission to build beneficial AI systems that are safe and reliable for users and society as a whole.