Jack & Jill
US - California - San Francisco
View Company Profile /
<< Go Back
You will design and manage multi-region GPU deployments to ensure reliable, high-performance inference. Collaborate with researchers to optimize CUDA hot paths for live AI conversations.
Requirements: The ideal candidate should have hands-on experience with large-scale GPU inference workloads and deep expertise in Kubernetes and EKS. A proven track record of senior technical leadership and ownership of infrastructure challenges is essential.
Key Skills: GPU Inference, CUDA, Kubernetes, EKS, Cloud Providers, Performance Optimization, Infrastructure Management, AI Conversations, Real-Time Processing, Multi-Region Deployments, Service Routing, Cluster Management, Technical Leadership, Workload Placement, Cold-Start Optimization
Benefits: Equity
© 2026 engineeringjobs.net, Inc. All Rights Reserved.
Terms of Service | Privacy
Powered by JOBBEX