Senior / Staff Software Engineer - Autonomous Agent Infrastructure

Who you are

You have 5+ years of experience in software engineering, particularly in building complex distributed systems. Your background includes a strong focus on security engineering, ensuring that systems are not only functional but also safe and reliable. You thrive in environments where you can design and implement innovative solutions that push the boundaries of technology.

Your expertise in Java is complemented by a deep understanding of state management systems and sandboxed environments. You have a proven track record of developing frameworks that enable secure interactions between AI agents and external services. You are comfortable working at the intersection of product development and engineering, collaborating closely with cross-functional teams to deliver impactful solutions.

You are a proactive problem solver who enjoys tackling challenging issues and finding creative ways to overcome obstacles. Your communication skills allow you to articulate complex technical concepts to non-technical stakeholders, fostering collaboration and understanding across teams. You are passionate about the potential of AI and are eager to contribute to projects that have a meaningful impact on society.

Desirable

Experience with observability and debugging tools for AI systems is a plus. Familiarity with authentication and authorization frameworks will enhance your ability to contribute to the security aspects of the role. A background in AI or machine learning is beneficial but not required.

What you'll do

In this role, you will design and build the infrastructure that enables Claude, Anthropic's AI, to perform tasks autonomously. This includes creating sandboxed compute environments where Claude can execute code safely and interact with external services. You will develop state management systems that handle long-running tasks, ensuring that checkpoints, recovery, and resumption across failures are seamless.

You will also be responsible for developing authentication and authorization frameworks that allow Claude to act securely on behalf of users. Your work will involve creating observability and debugging tools that provide insights into Claude's actions, helping to improve performance and reliability.

Collaboration is key in this role, as you will partner closely with product teams to align engineering efforts with user needs and business goals. You will engage in discussions about system architecture and design, contributing your expertise to shape the direction of the project. Your contributions will be vital in building the next generation of AI capabilities that are safe and beneficial for users.

What we offer

Anthropic is committed to fostering a collaborative and innovative work environment. We offer competitive compensation and benefits, including optional equity donation matching and generous vacation and parental leave. Our flexible working hours allow you to maintain a healthy work-life balance, and our office in San Francisco provides a welcoming space for collaboration with colleagues. Join us in our mission to create reliable and interpretable AI systems that benefit society as a whole.