1x Founding Infrastructure Engineer at VLM Run ( https://vlm.run )
On-site · United States
Core
Building and scaling the inference platform for visual intelligence, serving open-weight VLMs and embodied VLAs across a fleet of GPUs and clouds.
Role type
Founding Infrastructure Engineer
Builds
Unified API for visual intelligence models (VLMs, VLAs, ViTs) serving 100s of thousands of requests per day
Domain
AI / Computer Vision / Cloud Infrastructure
Required skills
Ray, Kubernetes, GPU management, serverless architectures, production ML infrastructure
Responsibilities
Design and implement scalable infrastructure for high-throughput VLM inference, manage GPU fleets and cloud resources, optimize system performance for serving visual intelligence models
