Software Engineer- BIS (Baseten Inference Stack)

Join Baseten’s Inference Stack to build and operate the distributed runtime powering large-scale LLM inference. Own production systems across the stack, from developer-facing deployment tooling to low-level infrastructure in Kubernetes, delivering high performance, reliability, and scalable inference. Collaborate across teams to optimize inference, routing, autoscaling, and observability for customers using cutting-edge AI models.