Staff Software Engineer, Inference

• Join the Inference team responsible for building and maintaining the critical systems that serve Claude to millions of users worldwide. • Work on the industry's largest compute-agnostic inference deployments, covering the entire stack from intelligent request routing to fleet-wide orchestration across diverse AI accelerators. • Tackle complex, distributed systems challenges across multiple accelerator families and emerging AI hardware running in multiple cloud platforms. • Serve hundreds of thousands of customers every day through sophisticated routing, scaling, and networking systems.

• Be proficient in Python or Rust. • Have software engineering experience building and operating distributed systems in production. • Have working knowledge of containerised infrastructure such as Kubernetes and at least one major cloud platform (AWS, GCP, or Azure). • Be results-oriented with a bias towards flexibility and impact. • Be willing to pick up slack, even if it goes outside your job description. • Have a desire to learn more about machine learning systems and infrastructure. • Thrive in environments where technical excellence directly drives both business results and research breakthroughs. • Care about the societal impacts of your work.

• Have significant experience with high-performance, large-scale distributed systems. • Have experience implementing and deploying machine learning systems at scale. • Have experience building load balancing, request routing, or traffic management systems. • Be familiar with LLM inference optimisation, batching, and caching strategies. • Have deep experience operating Kubernetes and cloud infrastructure at scale. • Have experience with AI accelerator platforms such as GPUs, TPUs, or emerging hardware.

• Design, build, and maintain the distributed systems that serve Claude to millions of users worldwide. • Develop resilient, flexible systems that adapt in real time to real-world events. • Develop intelligent request routing, load balancing, and traffic management systems across thousands of accelerators. • Maximise compute efficiency across the fleet by autoscaling and orchestrating production, research, and experimental workloads. • Build and operate production-grade deployment pipelines for releasing new models to users. • Provide high-performance inference infrastructure that enables researchers to develop next-generation models. • Integrate new AI accelerator platforms and support inference for new model architectures.

• Receive an annual salary of £325k–£390k GBP. • Work from the London office with a hybrid policy requiring at least 25% office time. • Receive visa sponsorship with every reasonable effort made and an immigration lawyer retained to help. • Receive competitive compensation and benefits with optional equity donation matching. • Receive generous vacation and parental leave. • Enjoy flexible working hours. • Apply at any time, as applications are reviewed on a rolling basis with no deadline.

Anthropic's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial for users and society. The company is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. Anthropic is a public benefit corporation headquartered in San Francisco with offices in London.