Staff Cloud Inference Engineer (Multi-Cloud)

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

Job summary

Anthropic Limited is seeking a backend engineer to design, build, and own cloud-based inference services for Claude across AWS, GCP, and Azure. You will work with cross-functional teams to ensure reliable, scalable, and cost-efficient deployment, handling capacity, routing, and observability in a high‑scale environment.

The role emphasizes autonomous ownership, collaboration with security and product teams, and building tooling for multi-cloud inference across providers.

Qualifications

• Significant software engineering experience in high-performance, distributed systems
• Experience with cloud platforms (AWS, GCP, or Azure) and Kubernetes
• Familiarity with Infrastructure as Code and container orchestration
• Interest in LLM serving; ML background not required
• Strong cross-functional collaboration skills
• Autonomous and ownership mindset

Responsibilities

• Design, build, and operate backend services for Claude across multiple CSPs
• Collaborate with inference, API, systems, and security teams and CSP partners
• Develop CI/CD pipelines to deploy model versions at scale
• Create cost-aware interfaces and tooling for multi-cloud inference
• Contribute to capacity planning, autoscaling, and routing strategies
• Analyze observability data to identify bottlenecks and cost anomalies

Job description

Anthropic Limited is seeking a backend engineer to design, build, and own cloud-based inference services for Claude across AWS, GCP, and Azure. You will work with cross-functional teams to ensure reliable, scalable, and cost-efficient deployment, handling capacity, routing, and observability in a high‑scale environment.

The role emphasizes autonomous ownership, collaboration with security and product teams, and building tooling for multi-cloud inference across providers.