C

Cast AI

Autonomous Kubernetes autoscaling and optimization

AI Solutions Architect

Implementation & Technical Account ManagementConfirmed live in the last 24 hours
Full-time

About the Job

Requirements

  • Deep hands-on experience with large language models, including deploying, fine-tuning, evaluating, or debugging them and comparing model performance for specific tasks.
  • Experience operating in a fast-moving environment that is prone to change.
  • Experience building or optimizing inference systems; understanding latency, throughput, and total cost of ownership; and estimating cost and performance implications.
  • Ability to explain complex inference concepts to non-machine-learning engineers and connect them to business impact.
  • Commercial understanding of revenue expansion, identifying customer expansion opportunities, and designing strategies to capture them, combined with technical excellence and entrepreneurial thinking.

Responsibilities

  • Lead hands-on demonstrations of Kimchi Coding, Studio, and Teleport inference products.
  • Set up Kimchi Studio workspaces in customer environments and help teams configure worktrees, integrations with Slack, repositories, and documentation, and skills so agents understand customer conventions.
  • Design and drive implementation of customer governance policies, including spending limits per team or developer, cost attribution by project, and model-routing preferences; ensure hard budget caps work for the organization.
  • Help teams integrate Kimchi's serverless inference API and optimize model selection and routing for coding, reasoning, and planning workloads.
  • Translate customer feedback into product input, highlighting agent failures, Studio user-experience issues, and governance policies that do not meet customer needs.

About the Company

Cast AI

Autonomous Kubernetes autoscaling and optimization

Cast AI automates Kubernetes management and cloud-cost optimization. Its engine learns from real clusters to predict needs, continuously rightsizes CPU/memory, and adjusts resources automatically to meet performance targets. It handles spot interruptions, uses agentic runbooks with approvals, and includes a Database Optimizer; for AI workloads, Kimchi.dev routes requests across SaaS and self-hosted models with data sovereignty, plus OMNI Compute to provision GPU capacity across clouds. The goal is to remove manual firefighting by making infrastructure run smoothly and cost-efficiently.

Company size
201-500
Company stage
Series C
Total funding
$185.8M
Headquarters
Miami, FL
Founded
2019

Recently Posted Jobs

Explore more opportunities at Cast AI

See more jobs