fal.ai
I’m on the infrastructure team, working on the GPU fleet and the services that run generative-media inference. My work covers provisioning, platform reliability, and storage across cloud providers.
GPU fleet
Provision and maintain GPU workers across multiple hyperscalers and cloud providers. I work on the infrastructure that supports the serverless GPU inference platform.
JuiceFS setup
Worked on the JuiceFS setup for fal’s infrastructure. My work focused on day-to-day maintenance, distributed storage performance, and reliability.
Python / GPUs / Kubernetes / Nomad