RustPythonKubernetesNCCLDistributed SystemsClaude AIHigh Performance Computing

Role Briefing: Build the ultra-reliable distributed training and inference clusters that power Claude 3.5 Sonnet and future frontier AI models at Anthropic.

Working at Anthropic

Anthropic is an AI safety and research company that builds reliable, interpretable, and steerable AI systems. The cluster computing team operates some of the largest compute clusters on Earth.

Your Role

Architect resilient distributed training frameworks that recover from node failures without losing training progress.

Write custom high-throughput communication kernels in Rust and C++ interfacing with NCCL and collective communication libraries.

← Return to All Tech Positions