Staff & Senior Software Engineer: AI Inference Systems

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

Benefits offered by this job

Equity donation matching

Generous vacation and parental leave

Flexible working hours

Job summary

Anthropic is expanding its Inference team in Seattle to scale Claude’s deployment. You will work on distributed inference infrastructure, real-time routing, and cross-cloud orchestration for millions of users.

The role focuses on efficiency, reliability, and large-scale systems that enable cutting-edge ML research. Ideal candidates have strong distributed systems experience, a passion for ML-scale infrastructure, and a drive to impact safety and reliability at scale.

Qualifications

• Significant software engineering experience in distributed systems.
• Bias towards flexibility and impact in delivery.
• Willingness to take on additional responsibilities beyond job description.
• Desire to learn more about machine learning systems and infrastructure.
• Thrive in environments where technical excellence drives results and breakthroughs.
• Care about societal impacts of work.

Responsibilities

• Design, build, and maintain distributed systems serving Claude to millions of users.
• Develop resilient, flexible systems responsive to real-world events.
• Create intelligent request routing, load balancing, and traffic management across accelerators and clouds.
• Maximize compute efficiency and control costs via autoscaling across production, research, and experiments.
• Build and operate deployment pipelines for new models.
• Provide high-performance inference infrastructure enabling researchers to prototype next-generation models.
• Integrate new accelerator platforms for inference across model architectures.

Skills

Distributed systems

Results-oriented

Flexibility

Learning mindset

Societal impact awareness

Education

Bachelor's degree

Tools

Kubernetes

AWS

GCP

Azure

Job description

Anthropic is expanding its Inference team in Seattle to scale Claude’s deployment. You will work on distributed inference infrastructure, real-time routing, and cross-cloud orchestration for millions of users.

The role focuses on efficiency, reliability, and large-scale systems that enable cutting-edge ML research. Ideal candidates have strong distributed systems experience, a passion for ML-scale infrastructure, and a drive to impact safety and reliability at scale.