Software Engineer, Agent Platform

About Anthropic

Anthropics mission is to create reliable interpretable and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers engineers policy experts and business leaders working together to build beneficial AI systems.

About the role:

At Anthropic were building AI systems that are helpful harmless and honest. Our mission is to develop AI that benefits humanity and we believe the most transformative capabilities emerge when we thoughtfully bridge the gap between research breakthroughs and real-world applications. Every new capability we develop has the potential to reshape how people work learn and create.

Frontier Apps serves as Anthropics innovation team exploring how emerging AI capabilities can transform user experiences and unlock entirely new ways for people to interact with AI systems. Within Frontier Apps the Agent Platform team focuses on building blocks that allow people to delegate large amounts of work to Claude.

We are seeking a versatile and collaborative Full Stack Engineer to join the Agent Platform this role you will work closely with customers product management and researchers to create reusable components that form the basis for powerful AI agents. Our work includes long-lived agents memory professional documents skills and evals for agentic capabilities. Youll be at the intersection of cutting-edge research and real-world application building capabilities that shape the future of human-AI interaction.

Responsibilities:

• Design and implement novel interaction patterns that allow AI systems to take meaningful action in real-world environments while maintaining safety and reliability
• Create new integrations that enable Claude to access enterprise data sources knowledge bases and third-party systems across industries
• Build sophisticated client-side applications with local state management optimized for performance even in constrained or high-latency environments
• Collaborate with Product teams to launch new agent capabilities into production and optimize user adoption
• Work with Research teams to leverage emerging model capabilities and provide feedback on how models can better utilize new kinds of integrations
• Coordinate across multiple teams at Anthropic to ensure prototypes integrate with existing infrastructure and capabilities
• Create clean abstractions and interfaces that work reliably across multiple platforms (GSuite Office 365 Slack etc.) and modalities (chat API desktop mobile)
• Partner closely with Applied AI field teams customers and early access partners to understand real-world needs and rapidly iterate on prototypes
• Build tools and evaluation frameworks that ensure agent capabilities work reliably across diverse environments and use cases

You might be a good fit if you:

• Have 3 years of software engineering experience with a focus on building integrations APIs or data infrastructure
• Are passionate about the potential of AI agents and eager to tackle cutting-edge challenges in human-machine collaboration
• Have experience building and deploying AI agents MCP servers or similar systems
• Possess strong practical coding skills and experience creating and deploying full stack applications
• Take a user-centric approach to development prioritizing solutions that are robust scalable and intuitive
• Thrive in a fast-paced collaborative environment and enjoy working closely with cross-functional partners and customers
• Have experience across a range of industries and company sizes from startups to large enterprises
• Are willing to contribute beyond your core responsibilities
• Want exposure to cutting-edge AI research and its practical applications
• Care about the societal impacts and ethics of your work

Strong candidates may also have experience with:

• Building new data and communications infrastructure
• Multiple modalities of user experiences and integrations (web mobile APIs webhooks etc.)
• Event-driven system development and real-time streaming data architectures
• Industries such as education finance healthcare transportation government or energy
• Software development or integration at companies that dont primarily create software
• Containerization cloud platforms and DevOps practices
• AI/ML systems and understanding their capabilities and limitations
• A vision for the future of AI agents and a drive to make that vision a reality

Logistics

Education requirements: We require at least a Bachelors degree in a related field or equivalent experience.

Location-based hybrid policy: Currently we expect all staff to be in one of our offices at least 25% of the time. However some roles may require more time in our offices.

Visa sponsorship:We do sponsor visas! However we arent able to successfully sponsor visas for every role and every candidate. But if we make you an offer we will make every reasonable effort to get you a visa and we retain an immigration lawyer to help with this.

We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy so we urge you not to exclude yourself prematurely and to submit an application if youre interested in this work. We think AI systems like the ones were building have enormous social and ethical implications. We think this makes representation even more important and we strive to include a range of diverse perspectives on our team.

How were different

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact advancing our long-term goals of steerable trustworthy AI rather than work on smaller and more specific puzzles. We view AI research as an empirical science which has as much in common with physics and biology as with traditional efforts in computer science. Were an extremely collaborative group and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic including: GPT-3 Circuit-Based Interpretability Multimodal Neurons Scaling Laws AI & Compute Concrete Problems in AI Safety and Learning from Human Preferences.

Come work with us!

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits optional equity donation matching generous vacation and parental leave flexible working hours and a lovely office space in which to collaborate with colleagues. Guidance on Candidates AI Usage:Learn aboutour policyfor using AI in our application process