1x Founding Infrastructure Engineer at VLM Run ( https://vlm.run )
Core
Building the inference platform for visual intelligence, specifically the VLM Run Gateway API that serves open-weight VLMs, embodied VLAs, and ViTs across a fleet of GPUs and clouds.
Role type
Founding Infrastructure Engineer
Builds
Unified API for visual intelligence models (VLMs, VLAs, ViTs) deployed on GPU fleets and cloud infrastructure
Domain
AI Infrastructure / Computer Vision / GPU Cloud
Deliverable
production ML models
Required skills
Docker, Kubernetes, GPU infrastructure management, cloud infrastructure, open-weight model serving
Preferred skills
Experience with autonomous driving or LLM infrastructure, PhD in AI/Computer Vision
Technologies
Docker, Kubernetes, GPUs, Cloud platforms
Responsibilities
Design and build the infrastructure for the VLM Run Gateway API, manage GPU fleets, optimize model serving performance
Seniority
Founding, hands-on IC