320K–485K USD / year
Staff + Sr. Software Engineer, Cloud Inference Launch Engineering
AIHybrid — San Francisco, CA | Seattle, WA
Published on 2026-09-28
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
The role involves working on the Cloud Inference team to optimize and scale Claude across various cloud platforms. You'll be responsible for the validation pipeline for inference servers and load balancers, ensuring that model launches and performance improvements are executed correctly and efficiently.
About the company
Anthropic builds reliable and interpretable AI systems, including the Claude family of models, for businesses and developers. The company focuses on AI safety research and practical AI assistants for enterprise and consumer use.
The team
Cloud Inference team
Stack
PythonRustAWSGCPAzureKubernetes
What you'll do
- Oversee frontier model launches and inference for new architectures
- Integrate new inference features to cloud platforms
- Identify and fix inference behavior gaps across platforms
- Design CI/CD infrastructure for inference server
- Improve validation speed and reliability
- Analyze observability data to address performance bottlenecks
What we're looking for
- Strong interest in LLM serving
- Significant software engineering experience
- Track record of building automation or test infrastructure
- Experience with major cloud platforms
- Collaboration skills with internal and external teams
- Ability to quickly learn new technologies
Nice to have
- LLM inference optimization skills
- Experience with multi-region deployments
- Familiarity with global traffic management
- Experience working with CSP partner teams
Benefits
- Equity donation matching
- Generous vacation and parental leave
- Flexible working hours