Senior Cloud Backend Engineer — Multi-Cloud Inference

Anthropic; Seattle (WA); Hybrid; USD 320,000 - 485,000; Full time

Job summary

Anthropic in Seattle, WA is seeking a backend engineer to design, build, and own cloud‑inference services running Claude across AWS, GCP, Azure, and future CSPs. You will shape the end‑to‑end serving stack, from API integration to inference execution and capacity planning, ensuring reliability and cost efficiency at scale.

You will collaborate with inference, product API, systems, and security teams, operate CI/CD pipelines, implement CSP‑level interfaces, and optimize routing, observability,

Qualifications

• Experience with large-scale distributed systems serving millions of users.
• Experience building or operating services on at least one major cloud platform with Kubernetes or IaC.
• Curious about LLM serving; prior inference or ML experience is not required.
• Thrives in cross-functional collaboration with internal teams and external partners.
• Able to learn new technologies quickly and take ownership of problems end-to-end.

Responsibilities

• Design, build, and own backend services across CSPs for Claude; account for compute, networking, APIs, and ops models.
• Collaborate with inference, product API, systems, and security teams and CSP partners to stand up the full serving stack on new clouds.
• Develop CI/CD pipelines to deploy model versions to millions of users with minimal regressions.
• Design interfaces and tooling across CSPs to enable cost-effective inference and cross-provider scalability.
• Contribute to capacity planning, autoscaling, and routing strategies to optimize cost and performance.
• Analyze observability data to identify bottlenecks and cost anomalies and drive remediation.

Skills

Distributed systems

Cloud platforms

Backend engineering

Kubernetes

Python or Rust

Education

Bachelor's degree

Tools

Kubernetes

CI/CD pipelines

Terraform

Job description

Anthropic in Seattle, WA is seeking a backend engineer to design, build, and own cloud‑inference services running Claude across AWS, GCP, Azure, and future CSPs. You will shape the end‑to‑end serving stack, from API integration to inference execution and capacity planning, ensuring reliability and cost efficiency at scale.

You will collaborate with inference, product API, systems, and security teams, operate CI/CD pipelines, implement CSP‑level interfaces, and optimize routing, observability,