Staff / Senior Software Engineer – Inference Deployment

About the role

Anthropic is looking for a Staff or Senior Software Engineer to join its Inference team in San Francisco. You will help build and operate the large‑scale, compute‑agnostic infrastructure that powers Claude for millions of users worldwide, ensuring high performance and reliability.

Key responsibilities

• Design, develop, and maintain distributed systems that serve AI models at massive scale.
• Implement resilient, real‑time routing, load‑balancing, and traffic‑management solutions across thousands of accelerators.
• Optimize compute efficiency through autoscaling, orchestration, and intelligent workload placement.
• Build production‑grade deployment pipelines for releasing new model versions.
• Provide high‑performance inference infrastructure that enables researchers to develop next‑generation models.
• Integrate emerging AI accelerator platforms and support new model architectures.

Required profile

• Significant software engineering experience, especially with large‑scale distributed systems.
• Results‑oriented mindset with a bias toward flexibility and impact.
• Willingness to take on tasks beyond the core job description.
• Interest in learning about machine‑learning systems and infrastructure.
• Commitment to the societal impact of AI technology.

Required skills

• Distributed systems engineering
• Load balancing and request routing
• Traffic management at scale
• Kubernetes orchestration
• Experience with AI accelerator hardware