Senior Cloud Inference Engineer for Frontier Models

Anthropic; San Francisco (CA); Hybrid; USD 320,000 - 485,000; Full time

Benefits offered by this job

Office space

Job summary

Anthropic is seeking a strong software engineer to join the Cloud Inference team, scaling Claude on AWS, GCP, Azure, and future CSPs. You will own the end-to-end inference platform, from API integration to capacity management and day-to-day operations.

You will lead improvements in validation, inference functionality, and cross-cloud portability, ensuring correctness, performance, and reliability across platforms. The role emphasizes autonomy, collaboration, and high-impact infrastructure work.

Qualifications

• Strong software engineering experience in high-performance, large-scale distributed systems serving millions of users.
• Experience building automation or test infrastructure that improved release velocity or reliability.
• Experience operating services on at least one major cloud platform (AWS, GCP, or Azure) with Kubernetes, IaC, or container orchestration.
• Ability to work cross-functionally with internal teams and external partners.
• Fast learner and highly autonomous with end-to-end ownership.

Responsibilities

• Be on the critical path for frontier model launches, bringing up inference for new model architectures and shipping them to cloud platforms in lockstep with our first-party platform
• Work with the core inference team to bring new inference features to cloud platforms, owning the platform-specific integration that gets them to production
• Identify and fix gaps causing inference variance across first-party and CSPs, including config drift, observability, and deployment patterns
• Design, build, and own the CI/CD infrastructure for the inference server and load balancer across cloud platforms with shadow traffic and performance baselines
• Drive down merge-to-production cycle time by making validation faster, more parallel, and cost-effective
• Analyze observability data to identify bottlenecks, cost anomalies, and regressions and drive remediation

Skills

Distributed systems

Cloud platforms (AWS/GCP/Azure)

Python or Rust

Automation / CI/CD

High-performance software

Education

Bachelor's degree in CS or related field

Tools

Kubernetes

Terraform

Docker

Job description

Anthropic is seeking a strong software engineer to join the Cloud Inference team, scaling Claude on AWS, GCP, Azure, and future CSPs. You will own the end-to-end inference platform, from API integration to capacity management and day-to-day operations.

You will lead improvements in validation, inference functionality, and cross-cloud portability, ensuring correctness, performance, and reliability across platforms. The role emphasizes autonomy, collaboration, and high-impact infrastructure work.