Staff Software Engineer, Inference

About Anthropic 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. About the role: 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. The team has a dual mandate: maximizing compute efficiency to serve our explosive customer growth, while enabling breakthrough research by giving our scientists the high-performance inference infrastructure they need to develop next-generation models. We tackle complex, distributed systems challenges across multiple accelerator families and emerging AI hardware running in multiple cloud platforms. As a Staff Software Engineer on our Inference team, you will work end to end, identifying and addressing key infrastructure blockers to serve Claude to millions of users while enabling breakthrough AI research. Strong candidates should have familiarity with performance optimization, distributed systems, large-scale service orchestration, and intelligent request routing. Familiarity with LLM inference optimization, batching strategies, and multi-accelerator deployments is highly encouraged but not strictly necessary. Strong candidates may also have experience with: - High-performance, large-scale distributed systems - Implementing and deploying machine learning systems at scale - Load balancing, request routing, or traffic management systems - LLM inference optimization, batching, and caching strategies - Kubernetes and cloud infrastructure (AWS, GCP) - Python or Rust You may be a good fit if you: - Have significant software engineering experience, particularly with distributed systems - Are results-oriented, with a bias towards flexibility and impact - Pick up slack, even if it goes outside your job description - Want 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 Representative projects across the org: - Designing intelligent routing algorithms that optimize request distribution across thousands of accelerators - 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 - Integrating new AI accelerator platforms to maintain our hardware-agnostic competitive advantage - Contributing to new inference features (e.g., structured sampling, prompt caching) - 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 Deadline to apply: None. Applications will be reviewed on a rolling basis. The annual compensation range for this role is listed below. For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role. Annual Salary: €295.000—€355.000 EUR Logistics Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience Required field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position 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 aren't 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 applica

Strong candidates should have significant software engineering experience, particularly with distributed systems. Familiarity with performance optimization, distributed systems, large-scale service orchestration, and intelligent request routing. Familiarity with LLM inference optimization, batching, and multi-accelerator deployments is highly encouraged but not strictly necessary. Potentially beneficial experience includes high-performance, large-scale distributed systems; implementing and deploying machine learning systems at scale; load balancing, request routing, or traffic management systems; LLM inference optimization, batching, and caching strategies; Kubernetes and cloud infrastructure (AWS, GCP); Python or Rust.

Identify and address infrastructure blockers to serve Claude to millions of users; work end to end on the Inference stack, including intelligent request routing and fleet-wide orchestration across diverse AI accelerators; design and implement routing algorithms for optimal distribution across thousands of accelerators; autoscale compute fleet to match supply with demand across production, research, and experimental workloads; build production-grade deployment pipelines for releasing new models to millions of users; integrate new AI accelerator platforms to maintain hardware-agnostic advantage; contribute to inference features (e.g., structured sampling, prompt caching); support inference for new model architectures; analyze observability data to tune performance based on real-world production workloads; manage multi-region deployments and geographic routing for global customers.