Anthropic
Staff + Senior Software Engineer, Inference Deployment
$320K–$485K
San Francisco, CA +5 · Staff · Full-time · Posted Jun 29, 2026
- Location
- San Francisco, CA
New York City, NY
Seattle, WA
New York, New York, United States
San Francisco, California, United States
Seattle, Washington, United States - Experience
- Significant software engineering experience; minimum years correlate with internal job level requirements.
- Education
- Bachelor’s degree or an equivalent combination of education, training, and/or experience; relevant field of study as demonstrated through coursework, training, or professional experience.
- Visa sponsorship
- Visa sponsorship is available, but not for every role or candidate; if an offer is made, the company will make every reasonable effort to obtain a visa.
About the job
Build and operate distributed inference systems that serve Claude, improve compute efficiency, and support research and deployment of new models.
What you'll do
- Design and maintain distributed systems, including intelligent routing, load balancing, and fleet orchestration.
- Build production deployment pipelines and integrate new accelerator platforms and model architectures.
- Provide high-performance inference infrastructure and tune performance using production observability data.
What they ask for
- Significant software engineering experience, particularly with distributed systems.
- Results-oriented approach, flexibility, and willingness to take on work beyond the job description.
- Desire to learn about machine learning systems and infrastructure.
- Care about the societal impacts of the work.
Nice to have
- Experience with large-scale distributed or machine learning systems, routing, load balancing, or traffic management.
- Familiarity with LLM inference optimization, Kubernetes, cloud infrastructure (AWS, GCP, Azure), Python, or Rust.
Pay
$320,000–$485,000 USD annual salary (base salary)
Tools
Kubernetes, AWS, GCP, Azure, Python, Rust
AI focus
Develop and operate high-performance inference infrastructure for Claude and other model architectures, supporting model research, deployment, and inference optimization.
Model-written summary · the original posting is authoritative