ML Infrastructure Engineer at zaimler

Zaimler is hiring an Inference and Model Serving Engineer to own the end-to-end infrastructure for inference and model serving, including Ray Serve, GPU infrastructure, and scalable agent orchestration. The role involves building and scaling production ML/AI platforms, optimizing model-serving engines, and integrating systems with data analysis and agent workflows. It requires at least three years of relevant experience, deep knowledge of the inference stack, and prior zero-to-one platform-building capability. The position is onsite in San Mateo and offers medical, dental, vision, 401k benefits, and H-1B visa sponsorship.