AI Multi-Region Model Deployment Engineer

Uelvex Cloud

Remote · $200k+ / year · Full-time · Posted 2 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

We just closed our Series A and are scaling fast — customer model traffic has grown 6x in the last two quarters and our single-region deployment setup is starting to show cracks. We need a senior engineer to lead the move to true multi-region model serving across AWS and GCP, with MLflow-tracked models deployed consistently everywhere and Kubernetes handling failover without waking anyone up at 3am. You'll design the deployment topology from scratch, working closely with the infra lead to make sure every region behaves identically under load. This is a build-it role, not a maintain-it role.

Responsibilities

Design and implement multi-region model serving across AWS and GCP
Build automated failover so regional outages don't require manual intervention
Standardize MLflow-based model packaging across all deployment targets
Own the Kubernetes infrastructure powering production model serving

Requirements

Deep production experience with Kubernetes at multi-region scale
Hands-on experience across both AWS and GCP
Familiarity with MLflow or a comparable model tracking and packaging tool
Track record designing infrastructure from a blank slate, not just maintaining it