Sail is the most cost-efficient API for the best open-source models. Pay per token with unbeatable prices, cut costs even further with completion windows, and start with $5 in monthly free credits. Backed by Kleiner Perkins and Sequoia.
About the role
Build a reliable systems that let us manage and share compute across clouds Implement scheduling algorithms that maximize GPU utilization Found on 1752vc Careers, the job board for startup and VC roles.
What they're looking for
- Deep understanding of Kubernetes and related technology
- You take a product-focused approach to platform work and care deeply about building solutions that are robust, scalable, and ergonomic for users
- Bonus: experience with cluster virtualization technology like k3k or vCluster
More about this role
Sail builds the world's most efficient software for inference (processing LLM tokens) and agent hosting (cloud VMs). Together, our technologies allow our customers to deploy AI agents at extreme scale for their most ambitious work.
In this role, you'll focus on our clusters and associated infrastructure. You’ll be an early engineer on a rapidly growing product line and write code that automatically provisions and manages large fleets of compute.
Build a reliable systems that let us manage and share compute across clouds
Implement scheduling algorithms that maximize GPU utilization
Design and implement highly-available systems that route around hardware faults and swap in hot spares to deliver users are pristine experience on unreliable hardware
Implement wraparound monitoring and altering to ensure high availability
Own future directions for Clusters (fully autonomous remediation, self-serve ops, bare-metal provisioning, etc.).
Deep understanding of Kubernetes and related technology.
You take a product-focused approach to platform work and care deeply about building solutions that are robust, scalable, and ergonomic for users.
Bonus: experience with cluster virtualization...
Browse similar: Startup jobs · San Francisco Bay Area