VLM Run ()
Open positions
1 job
16 views last month
1x Founding Infrastructure Engineer
Open 31d North AmericaFull-time
United States
In-Person (Bay Area)Founding infrastructure engineer at VLM Run, an AI startup whose product is a unified inference gateway serving visual-language models, ViTs and VLAs across fleets of GPUs and clouds. You own and scale the ML serving infrastructure (Ray, Kubernetes, GPUs, serverless) handling hundreds of thousands of requests per day, working fully onsite in the Bay Area.
AI API Computer Vision GitHub Kubernetes +3 skills