Staff Software Engineer (Inference)

Location: London, UK; hybrid policy requires staff to be in one of the offices at least 25% of the time

Annual salary: £325,000–£390,000 GBP

Company

Anthropic develops reliable, interpretable, and steerable AI systems intended to be safe and beneficial for users and society.

What you will do

• Design, build, and operate distributed inference systems serving Claude to millions of users.
• Develop intelligent request routing, load balancing, traffic management, autoscaling, and fleet orchestration across thousands of accelerators.
• Build production-grade deployment pipelines for releasing new models to users.
• Provide high-performance inference infrastructure for machine learning research and next-generation models.
• Integrate new AI accelerator platforms and support new model architectures.
• Analyze observability data and manage multi-region deployments and geographic routing.

Requirements

• Proficiency in Python or Rust.
• Production experience building and operating distributed systems.
• Working knowledge of containerized infrastructure such as Kubernetes and at least one major cloud platform: AWS, GCP, or Azure.
• Bachelor’s degree or equivalent education, training, or professional experience in a relevant field.
• Ability to work flexibly, take ownership beyond a formal job description, and learn machine learning systems and infrastructure.
• Visa sponsorship is available, subject to role and candidate eligibility.

Nice to have

• Significant experience with high-performance, large-scale distributed systems.
• Experience deploying machine learning systems at scale and building load balancing or request-routing systems.
• Familiarity with LLM inference optimization, batching, and caching.
• Deep experience operating Kubernetes and cloud infrastructure at scale.
• Experience with GPUs, TPUs, or emerging AI accelerator hardware.

Culture & Benefits

• Collaborative work across research, engineering, policy, and business disciplines.
• Frequent research discussions focused on high-impact AI safety and research goals.
• Flexible working hours and office collaboration.
• Generous vacation and parental leave.
• Competitive benefits and optional equity donation matching.

Hiring process

• Applications are reviewed on a rolling basis; there is no application deadline.
• Candidate AI usage is governed by Anthropic’s application-process guidance.