Staff AI Inference Systems Engineer

Anthropic Limited; San Francisco (CA); On-site; USD 320,000 - 485,000; Full time

Benefits offered by this job

Equity donation matching

Generous vacation

Parental leave

Flexible hours

Office in San Francisco

Job summary

Anthropic in San Francisco seeks engineers to design, build, and operate distributed systems powering Claude for millions of users. You will work on scalable inference infrastructure and intelligent routing across multiple clouds, accelerating research and deployment of new models.

The role emphasizes performance, reliability, and collaboration with researchers while enabling societal impact through steerable AI systems.

Qualifications

• Experience designing and building large-scale distributed systems.
• Interest in machine learning infrastructure and inference workloads.
• Ability to operate across cloud providers and accelerate compute for ML models.

Responsibilities

• Design, build, and maintain distributed systems serving Claude to millions of users.
• Develop resilient, flexible systems that adapt to real-world events.
• Implement intelligent request routing, load balancing, and traffic management across accelerators and clouds.
• Maximize compute efficiency via autoscaling and orchestration of production, research, and experimental workloads.
• Build and operate deployment pipelines for releasing new models to users.
• Provide high-performance inference infrastructure to enable researchers to develop next-gen models.
• Integrate new AI accelerator platforms for inference of new architectures.

Skills

Distributed systems

ML infrastructure

Python or Rust

Problem solving

Adaptability

Education

Bachelor's degree or equivalent in relevant field

Tools

Kubernetes

AWS

GCP

Azure

Job description

Anthropic in San Francisco seeks engineers to design, build, and operate distributed systems powering Claude for millions of users. You will work on scalable inference infrastructure and intelligent routing across multiple clouds, accelerating research and deployment of new models.

The role emphasizes performance, reliability, and collaboration with researchers while enabling societal impact through steerable AI systems.