Research Engineer – Cybersecurity RL

Who you are

You have a strong background in cybersecurity, ideally with experience in secure coding and vulnerability remediation. Your expertise may come from being a white hat hacker or a security engineer, and you are curious about how AI can enhance your work in this field. You possess a solid understanding of reinforcement learning and have a keen interest in developing safe AI models. You thrive in collaborative environments, working alongside researchers and engineers to push the boundaries of AI technology.

You are proficient in Python and have experience with machine learning frameworks. Your technical skills allow you to design and implement reinforcement learning environments effectively. You are comfortable conducting experiments and evaluations, and you have a track record of delivering your work into production training runs. You are detail-oriented and have a strong analytical mindset, enabling you to assess the impact of your contributions on AI systems.

You are a proactive communicator, able to articulate complex ideas clearly to both technical and non-technical stakeholders. You enjoy collaborating with a diverse team of experts, sharing knowledge, and learning from others. You are committed to creating reliable and interpretable AI systems that are beneficial for users and society.

Desirable

Experience with AI safety and interpretability is a plus. Familiarity with defensive cybersecurity practices and tools will enhance your contributions to the team. If you have worked on projects involving AI in cybersecurity, that experience will be highly valued. A passion for advancing the field of AI and a desire to make a positive impact on society will set you apart.

What you'll do

As a Research Engineer on the Cybersecurity RL team, you will play a critical role in advancing Anthropic's AI systems. Your primary responsibilities will include designing and implementing reinforcement learning environments tailored for cybersecurity applications. You will conduct experiments to evaluate the effectiveness of your approaches, ensuring that they contribute to the safe advancement of AI capabilities.

You will collaborate closely with other researchers, engineers, and cybersecurity specialists to develop novel approaches that enhance secure coding practices and vulnerability remediation. Your work will involve translating research findings into practical implementations, delivering your contributions into production training runs that impact the performance of Anthropic's models.

You will engage in continuous learning and experimentation, staying up-to-date with the latest advancements in both AI and cybersecurity. Your insights will help shape the direction of the Cybersecurity RL team, and you will have the opportunity to contribute to significant projects that push the boundaries of what AI can achieve in the realm of security.

What we offer

Anthropic is committed to creating a supportive and collaborative work environment. We offer competitive compensation and benefits, including optional equity donation matching and generous vacation and parental leave. You will have flexible working hours and the opportunity to work in a lovely office space in either San Francisco or New York. Our mission is to build beneficial AI systems, and we encourage you to apply even if your experience doesn't match every requirement. Join us in making a positive impact on the future of AI.