About the Role
fal is building the fastest and most scalable infrastructure for AI inference. Fal Serverless powers 1,300+ endpoints on the fal Marketplace and handles tens of millions of requests per day across production workloads. Enterprises use fal Serverless to deploy, operate, and scale custom AI models without managing infrastructure themselves.
Autoscaling, observability, and operational complexity are handled end-to-end by fal’s platform and UI. Serverless began a