AI Platform Engineer - Kubernetes, Cloud & LLMs

Cast AI; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

Cast AI seeks a platform engineer to design and build the systems behind our AI assistant, including agent flows, context retrieval, and data connections. You will contribute to a public MCP server with strict safety gates and expand cloud connectivity across AWS, GCP, and Azure.

Production Go services will interact with cloud APIs, the Kubernetes control plane, and LLM APIs in real time. You will own features end-to-end, debug scaling challenges, and help shape product direction while joining a

Qualifications

• The role focuses on designing and building scalable systems for an AI assistant that reasons over production Kubernetes clusters.
• Production Go services development that interact with cloud provider APIs, Kubernetes, and LLMs in real time.
• Experience with multi-cloud environments and automation tooling is valuable.

Responsibilities

• Design and build the systems behind our AI assistant: agent flows, context retrieval, and data connections.
• Develop and maintain the public, permission-aware MCP server with curated tools, identity, audit and safety gates.
• Synchronize cloud connectivity across AWS, GCP, and Azure and support the data foundations for agents.
• Write production Go services that interact with cloud APIs, Kubernetes control plane, and LLM providers.
• Own features end-to-end from design through testing to production rollout (typical projects ship in 1–4 weeks).
• Debug novel problems like wrong agent answers, cross-cloud permission edge cases, and data freshness at scale.
• Build a quality harness with evals, telemetry, and feedback loops to ship improvements without regressions.
• Contribute to product direction and backlog; participate in on-call rotation.

Job description

Cast AI seeks a platform engineer to design and build the systems behind our AI assistant, including agent flows, context retrieval, and data connections. You will contribute to a public MCP server with strict safety gates and expand cloud connectivity across AWS, GCP, and Azure.

Production Go services will interact with cloud APIs, the Kubernetes control plane, and LLM APIs in real time. You will own features end-to-end, debug scaling challenges, and help shape product direction while joining a