About Shadeform
Shadeform is an aggregated GPU cloud that provides AI infrastructure to startups, scale ups, and enterprises.
AI infrastructure has become increasingly decentralized and AI workloads have progressively moved outside of the big 3 cloud providers. However, the emerging landscape of AI infrastructure, neoclouds, and AI factories are difficult to navigate and difficult to build on top of.
Rather than building out CapEx intensive data centers and hardware deployments, Shadeform glues together the decentralized data center and cloud provider environment by providing a uniform AI cloud platform, APIs, and services. Leading inference providers, enterprises, and hundreds of startups rely on Shadeform for their AI workloads.
About the Role
As a member of Shadeform’s engineering team, your core responsibilities will be building and maintaining the Shadeform GPU platform and building out automated, reusable services for customers. Shadeform relies on API routing and virtualization for gluing together infrastructure. Because Shadeform does not own its own data center and hardware, you will work on novel solutions to managing constrained and decentralized GPUs.
Preferred Experience
- Experience with virtualization technologies such as Kubevirt, OpenStack, or equivalent
- Experience with Kubernetes including the development of custom resources and managing controllers
- Experience with GPU specific orchestration, testing, and fleet management
Technical Stack
- Golang and Next.js; we expect everyone to be language agnostic
- AWS / GCP
- Kuberenetes
- Virtualization technologies such as KVM and Kubevirt
Location
- Remote in a US timezone; US preferred; cannot sponsor visas at this time