Ai Research Engineer • Mid-Level

Who you are

You have a strong background in AI research and engineering, with a focus on safety and security in autonomous systems. Your experience includes working on applied research projects that have real-world implications, particularly in the context of advanced AI technologies. You are committed to understanding the capabilities and risks associated with self-improving AI systems, and you are passionate about contributing to the development of defenses against potential adversarial uses of these technologies.

You thrive in collaborative environments, working alongside researchers, engineers, and policy experts to create beneficial AI systems. Your ability to communicate complex ideas clearly and effectively is one of your key strengths, allowing you to contribute to discussions that shape the direction of AI safety research. You are also comfortable navigating the intersection of technical research and policy, understanding how your work can influence decisions at the highest levels of the organization.

What you'll do

As a Research Engineer on the Frontier Red Team, you will focus on critical questions surrounding the defense against powerful autonomous AI systems. Your primary responsibilities will include building and evaluating model organisms of these systems, as well as developing the defensive agents necessary to counter them. This work is at the forefront of AI capabilities research, and your findings will directly inform how Anthropic and the broader community prepare for the challenges posed by advanced AI.

You will engage in early-stage, high-conviction research that has the potential for outsized impact, contributing to public demonstrations and shaping the understanding of AI safety. Your role will involve close collaboration with a diverse team, ensuring that the insights gained from your research are effectively integrated into the company's strategies and policies.

What we offer

Anthropic is committed to creating a supportive and innovative work environment. We offer competitive compensation and benefits, including optional equity donation matching, generous vacation and parental leave, and flexible working hours. Our office in San Francisco provides a collaborative space where you can work closely with colleagues who share your commitment to building safe and beneficial AI systems.