Software Engineer (Python, API)

About The Company

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We are committed to developing AI technologies that are safe and beneficial for our users and society as a whole. Our team consists of a rapidly growing group of dedicated researchers, engineers, policy experts, and business leaders who collaborate to build advanced and responsible AI systems. Headquartered in San Francisco, Anthropic operates as a public benefit corporation, emphasizing both innovation and ethical considerations in AI development.

About The Role

We are seeking skilled engineers to join our Inference team, which plays a critical role in building and maintaining the systems that serve Claude, our AI model, to millions of users worldwide. The team manages the entire stack involved in serving AI models, including intelligent request routing, fleet-wide orchestration, and integration across diverse AI accelerators. This role involves working with highly performance-sensitive distributed systems that operate at scale across multiple cloud platforms and hardware accelerators. The ideal candidate will contribute to developing resilient, flexible, and efficient inference infrastructure that supports both production workloads and cutting-edge AI research.

Qualifications

• Proficiency in Python or Rust programming languages
• Software engineering experience building and operating distributed systems in production
• Working knowledge of containerized infrastructure such as Kubernetes
• Experience with at least one major cloud platform (AWS, GCP, or Azure)
• Results-oriented mindset with flexibility and impact focus
• Willingness to take initiative beyond defined job responsibilities
• Desire to learn about machine learning systems and infrastructure
• Ability to thrive in environments where technical excellence drives business and research outcomes
• Awareness of the societal impact of AI technologies
  
  

Preferred Qualifications

• Significant experience with high-performance, large-scale distributed systems
• Experience implementing and deploying machine learning systems at scale
• Expertise in load balancing, request routing, and traffic management systems
• Familiarity with large language model (LLM) inference optimization, batching, and caching strategies
• Deep experience operating Kubernetes and cloud infrastructure at scale
• Experience with AI accelerator platforms such as GPUs, TPUs, or emerging hardware
  
  

Responsibilities

• Design, build, and maintain distributed systems serving Claude to millions of users
• Develop resilient and adaptive systems that respond to real-world events in real time
• Create intelligent request routing, load balancing, and traffic management systems across thousands of accelerators
• Maximize compute efficiency by autoscaling and orchestrating production, research, and experimental workloads
• Build and operate production-grade deployment pipelines for releasing new AI models reliably
• Provide high-performance inference infrastructure to enable researchers in developing next-generation AI models
• Integrate new AI accelerator platforms and support inference for new model architectures
• Analyze observability data to optimize system performance based on production workloads
• Manage multi-region deployments and geographic routing to support global customers
  
  

Benefits

• Competitive annual salary range of £325,000—£390,000 GBP
• Optional equity donation matching program
• Generous vacation and parental leave policies
• Flexible working hours and hybrid work policy with at least 25% on-site presence
• Support for visa sponsorship with dedicated immigration legal assistance
• Collaborative and inclusive work environment with frequent research discussions
• Access to a modern office space located in San Francisco
  
  

Equal Opportunity

Anthropic is an equal opportunity employer. We are committed to fostering a diverse and inclusive workplace where all employees feel valued and respected. We encourage applications from candidates of all backgrounds, including those from underrepresented groups in technology and AI research. We recognize the importance of diverse perspectives in advancing the ethical and societal impact of AI systems. Applicants should not feel discouraged if they do not meet every qualification listed, as we value potential and a willingness to learn.