Staff + Senior Software Engineer, Inference

Highlights

• Build systems serving Claude to millions of users worldwide daily.
• Design intelligent routing and autoscaling across thousands of accelerators.
• Enable breakthrough research with high-performance inference infrastructure.

What they offer

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Collaborative office space

Ideal candidate

A results-oriented distributed systems engineer who thrives on high-impact, flexible work and cares deeply about AI safety and societal impact, eager to learn ML infrastructure.

Requirements

• Significant software engineering experience, particularly with distributed systems
• Results-oriented with bias toward flexibility and impact
• Willing to pick up work outside job description
• Desire to learn machine learning systems and infrastructure
• Thrive where technical excellence drives business and research breakthroughs
• Care about societal impacts of work
• Bachelor's degree or equivalent combination of education and experience in a relevant field
• Experience with high-performance, large-scale distributed systems (preferred)
• Experience implementing and deploying ML systems at scale (preferred)
• Experience with load balancing, request routing, or traffic management (preferred)
• Familiarity with LLM inference optimization, batching, and caching (preferred)
• Experience with Kubernetes and cloud infrastructure such as AWS, GCP, Azure (preferred)
• Proficiency in Python or Rust (preferred)