Staff / Senior Software Engineer – Cloud Inference

About the role

Anthropic is looking for a Staff‑level or Senior Software Engineer to lead the Cloud Inference team. You will own the end‑to‑end delivery of Claude’s inference services across major cloud providers, ensuring reliability, performance and cost‑effectiveness at massive scale.

Key responsibilities

• Design, build and operate backend services that run Claude on AWS, GCP, Azure and future CSPs, handling differences in hardware, networking and APIs.
• Collaborate with internal inference, product, systems and security teams as well as cloud‑partner engineers to launch and maintain the full serving stack.
• Develop and maintain CI/CD pipelines that safely deploy new model versions to millions of users without regressions.
• Create abstractions and tooling that simplify cost‑effective inference management across providers.
• Drive capacity planning, autoscaling and request routing to match supply with demand and optimise cost.
• Monitor observability data, identify performance bottlenecks or cost anomalies, and implement remediation in production.

Required profile

• Significant software engineering experience building high‑performance, large‑scale distributed systems serving millions of users.

Required skills

• Backend services and infrastructure engineering.
• Experience with major cloud platforms (AWS, GCP, Azure).
• CI/CD automation and deployment pipelines.
• Capacity planning and autoscaling strategies.
• Observability, performance analysis and cost optimisation.