Staff Software Engineer, Cloud Inference

We are seeking an experienced backend Software Engineer to join Anthropic's Cloud Inference team. You will help architect, build, and scale Anthropic's cloud offerings that make our large language models available to customers across multiple platforms. Working across cloud ecosystems gives you a unique vantage point to identify and solve complex distributed systems challenges. You will solve technical challenges in safety, security, efficiency, and reliability while collaborating strategically with major cloud partners to enable frontier AI capabilities. Your work will enable customers to integrate our AI capabilities in their applications. Responsibilities: - Scale model serving infrastructure – You will architect and develop systems to meet growing demand while maintaining strict safety, security, efficiency, and reliability requirements across multiple cloud platform deployments. - Optimize accelerator utilization – Accelerator chips are gold in the AI world. You will help measure and optimize the allocation of chips serving Anthropic's models, playing a key role in helping these precious resources go to their best possible use. - Strategic external collaboration – You will work closely with major cloud platforms to implement and optimize frontier AI capabilities across their ecosystems, building strong technical partnerships that advance our long-term goals. - Build and operationalize infrastructure – You will work to improve and extend the core infrastructure needed to package, test, and deploy Anthropic's inference technology across multiple platforms. This work is a force-multiplier as it accelerates our ability to reliably launch new models and features to customers. - Implement trust and safety measures– AI safety is core to Anthropic's mission. You will help design and implement safety measures directly into our APIs and infrastructure to ensure consistent protection across all platforms. - Contribute to Anthropic's core mission - with your innovative ideas and system architecture enhancements to build ever-better beneficial AI systems.

Anthropic's 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.