Research Scientist • Senior

Who you are

You have a strong background in cybersecurity and AI, with experience in developing defenses against advanced threats — your expertise allows you to understand the implications of AI in cyber capabilities and how to mitigate risks effectively. You are familiar with the latest advancements in AI technologies and their potential applications in cybersecurity, enabling you to contribute to innovative research and development efforts.

You possess excellent problem-solving skills and can think critically about complex systems — your analytical mindset helps you identify vulnerabilities and devise strategies to enhance security measures. You are a collaborative team player, eager to work with cross-functional teams including security, safeguards, and policy experts to create impactful solutions.

You have a passion for research and a desire to make the world safer in the era of advanced AI — your commitment to ethical AI practices drives your work, ensuring that the systems you help develop are reliable and beneficial for society. You are comfortable working in a fast-paced environment and can adapt to the evolving landscape of AI and cybersecurity.

Desirable

Experience with self-improving AI systems or cyberphysical capabilities would be a plus — your familiarity with these areas can enhance the team's research efforts and contribute to groundbreaking advancements in AI safety. A background in robotics or cyberdefense is also advantageous, as it aligns with the team's focus on understanding and mitigating AI-related threats.

What you'll do

As a Senior Research Scientist on the Frontier Red Team, you will lead efforts to build tools and frameworks that defend against AI-enabled cyber threats — your work will involve researching the capabilities of large language models and agents in cybersecurity domains, aiming to stay ahead of potential risks. You will collaborate with various teams to shape and grow Anthropic's cyberdefense research program, ensuring that the organization is prepared for the challenges posed by advanced AI technologies.

You will conduct in-depth research to understand the implications of AI advancements on cybersecurity, developing strategies to counteract emerging threats — your findings will directly influence the development of security measures and policies within the organization. You will also mentor junior researchers, sharing your knowledge and expertise to foster a culture of learning and innovation within the team.

Your role will require you to stay informed about the latest trends and developments in AI and cybersecurity, allowing you to contribute to discussions and decision-making processes that shape the future of the organization's research initiatives. You will have the opportunity to present your research findings to stakeholders and contribute to the broader conversation about AI safety and ethics.

What we offer

Anthropic provides a supportive work environment where you can collaborate with a diverse team of experts dedicated to building beneficial AI systems — you will have access to competitive compensation and benefits, including flexible working hours and generous vacation policies. The company values your contributions and encourages you to take ownership of your work, providing opportunities for professional growth and development.

You will be part of a mission-driven organization focused on creating reliable and interpretable AI systems — your work will have a meaningful impact on society, as you contribute to making the world safer in an era of advanced AI. The office in San Francisco offers a collaborative space where you can engage with colleagues and share ideas, fostering a culture of innovation and creativity.