Staff Software Engineer, Inference

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 syst...

Our Inference team is responsible for building and maintaining the critical systems that serve Claude to millions of users worldwide. We bring Claude to life by serving our models via the industry's largest compute-agnostic inference deployments. We are responsible for the entire stack from intelligent request routi...

Inference systems are highly performance sensitive distributed systems. Inference serves hundreds of thousands of customers every day, and the size & span of the inference fleet requires sophisticated routing, scaling, and networking systems. We tackle complex, distributed systems challenges across multiple accelera...

Our Inference team is responsible for building and maintaining the critical systems that serve Claude to millions of users worldwide. We bring Claude to life by serving our models via the industry's largest compute-agnostic inference deployments. We are responsible for the entire stack from intelligent request routing to fleet-wide orchestration across diverse AI accelerators.
Inference systems are highly performance sensitive distributed systems. Inference serves hundreds of thousands of customers every day, and the size & span of the inference fleet requires sophisticated routing, scaling, and networking systems. We tackle complex, distributed systems challenges across multiple accelerator families and emerging AI hardware running in multiple cloud platforms.
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
Maximize 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

Proficiency in Python or Rust
Software engineering experience building and operating distributed systems in production
Working knowledge of containerized infrastructure (e.g., Kubernetes) and at least one major cloud platform (AWS, GCP, or Azure)
Results-oriented, with a bias towards flexibility and impact
Willingness to pick up slack, even if it goes outside your job description
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
Significant experience with high-performance, large-scale distributed systems
Experience implementing and deploying machine learning systems at scale
Experience building load balancing, request routing, or traffic management systems
Familiarity with LLM inference optimization, batching, and caching strategies
Deep experience operating Kubernetes and cloud infrastructure at scale
Experience with AI accelerator platforms (GPUs, TPUs, or emerging hardware)
Designing intelligent routing algorithms that optimize request distribution across many accelerators in different environments
Autoscaling our compute fleet to dynamically match supply with demand across production, research, and experimental workloads
Building production-grade deployment pipelines for releasing new models to millions of users reliably
Contributing to new inference features
Supporting inference for new model architectures
Analyzing observability data to tune performance based on real-world production workloads
Managing multi-region deployments and geographic routing for global customers