S

Sail Research

Open-source AI inference for autonomous agents

Member of Technical Staff - Clusters

Platform EngineeringUpdated on Nov 9
Full-timeSan Francisco, CA, USANo salary listed

About the Job

Requirements

  • Deep understanding of Kubernetes and related technology.
  • A product-focused approach to platform work, with a commitment to building robust, scalable, and ergonomic solutions for users.

Responsibilities

  • Build reliable systems that 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 use hot spares to provide a reliable user experience on unreliable hardware.
  • Implement monitoring and alerting to ensure high availability.
  • Own the future direction of Clusters, including autonomous remediation, self-serve operations, and bare-metal provisioning.

Desired Qualifications

  • Experience with cluster virtualization technology such as k3k or vCluster.

About the Company

Sail Research

Open-source AI inference for autonomous agents

Sail Research provides AI inference services for open-source models at scale to power autonomous background agents. It offers a private-beta OpenAI-compatible API that supports open models like Deepseek, Kimi, and Qwen, plus fine-tuned versions, enabling token-serving for customers. It handles end-to-end work, including CUDA GPU optimization, tweaking inference engines, and distributing workloads across multiple providers with spot compute to reduce costs. Its goal is to help autonomous agents make meaningful independent progress on complex problems by delivering reliable, scalable, and affordable open-model inference through an OpenAI-compatible API.

Company size
11-50
Company stage
Series A
Total funding
$80M
Headquarters
San Francisco, CA
Founded
2026

Recently Posted Jobs

Explore more opportunities at Sail Research

See more jobs