Job Description

As a founding infrastructure engineer, you will own the infrastructure for the inference platform for visual intelligence. You will work on production-grade ML infrastructure across GPUs and multiple clouds, help scale the VLM Run Gateway API that serves open-weight VLMs, embodied VLAs, and ViTs, and collaborate with a veteran team of AI researchers and engineers. The role requires building and maintaining scalable systems with Docker and Kubernetes, and delivering reliable, low-latency infrastructure. Please share your GitHub profile and recent projects (especially with Docker, Kubernetes, and GPUs) when applying.