Staff + Senior Software Engineer, Inference Deployment

What this role involves

The Launch Engineering team at Anthropic is responsible for automating the deployment of inference code across GPU, TPU, and Trainium fleets. The role involves designing deployment orchestration, improving capacity-aware scheduling, and reducing cycle time from merge to production. This position requires strong software engineering skills with a focus on complex state machines and multi-stage pipelines.

Skills this posting asks for

• deployment orchestration
• pipeline design
• observability
• capacity planning
• state machines
• fleet rollout
• inference deployment
• validation automation
• model onboarding
• systems engineering
• accelerator chips
• gpu
• tpu
• trainium

Requirements

• Level: staff

From the employer’s posting

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, en…