Jack & Jill
US - California - San Francisco
View Company Profile /
<< Go Back
Design and manage multi-region GPU deployments and EKS clusters to power real-time AI conversations with sub-second latency. Collaborate with researchers to optimize CUDA hot paths and reduce cold-start times for global AI video interfaces.
Requirements: Requires hands-on experience deploying large-scale GPU inference workloads on providers like AWS or CoreWeave. Candidates must have deep expertise in Kubernetes/EKS and a proven track record of senior technical leadership in infrastructure.
Key Skills: GPU Inference, Kubernetes, Amazon EKS, CUDA, Infrastructure Design, Cloud Deployment, Service Routing, Cluster Management
Benefits: Equity
© 2026 engineeringjobs.net, Inc. All Rights Reserved.
Terms of Service | Privacy
Powered by JOBBEX