Staff + Sr. Software Engineer, Cloud Inference
Core
Design, build, and own backend services and infrastructure to scale Claude across multiple cloud service providers (AWS, GCP, Azure), managing inference execution, capacity, and routing.
Role type
Staff/Senior backend software engineer (cloud inference)
Builds
End-to-end serving stack for LLMs across heterogeneous cloud platforms
Domain
Cloud infrastructure, Large Language Model (LLM) serving, Distributed systems
Deliverable
production ML models
Required skills
High-performance distributed systems, Cloud platform expertise (AWS/GCP/Azure), Kubernetes, Infrastructure as Code, Cross-functional collaboration, External partner management, Autonomous ownership
Preferred skills
Multi-cloud scaling experience, Capacity management, Cost optimization, Multi-region deployments, Python, Rust
Technologies
Kubernetes, AWS, GCP, Azure, Python, Rust
Responsibilities
Design backend services and abstractions for multi-cloud inference, Build CI/CD automation for model deployment, Manage capacity planning and autoscaling strategies, Analyze observability data for performance and cost optimization, Collaborate with internal teams and CSP partners to launch new platforms
Seniority
Staff/Senior, hands-on IC