Software Engineer | AI Agents & Cloud Platform (Cast Pilot team)

Cast AI; United States; A distancia; USD 140.000 - 210.000; Jornada completa

Descripción de la vacante

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

Formación

• 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.

Responsabilidades

• 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.

Descripción del empleo

Задачи:

A platform engineer opens their AI client of choice, connects it to CAST AI, and types: "Why did our spend jump 40% in eu-west last week?" Thirty seconds later they have an answer, pulled from live cluster state and cost data, with links back to the evidence. No dashboards. No YAML archaeology. Just a question and a correct, permission-checked answer. Your job is to make that interaction boring. Reliably, securely, at production scale. Behind it sits the hard part: an AI assistant that reasons over thousands of production Kubernetes clusters, a platform that safely exposes company infrastructure to external AI clients, and quality pipelines that tell us when the agent is wrong before a customer does. Get it right, and operators stop clicking through consoles entirely. Get it wrong once, and an agent gives a confidently wrong answer to someone managing production. CAST AI already runs Kubernetes infrastructure autonomously. Our automation makes thousands of cost-and-reliability decisions a day. Cast Pilot is the team building the intelligence layer on top of that: AI assistants for Kubernetes and the cloud itself. Our assistant already answers thousands of questions a month from hundreds of organizations. Now we're opening the platform up: a public, permission-aware MCP server so customers can plug CAST AI straight into their own AI clients and agents, deeper connectivity across all three major clouds (AWS, GCP, Azure), and a continuous push to make our agents smarter, better grounded, and more capable. This is greenfield AI platform work on top of battle-tested infrastructure. Most features ship in 1 to 4 weeks. This is a location-specific opportunity. We are currently accepting applications from candidates residing in the following European countries: Bulgaria, Croatia, Estonia, Greece, Hungary, Latvia, Lithuania, Poland, Romania, Slovakia, Cyprus, Malta, Finland, Sweden, Ireland, Moldova, North Macedonia, Montenegro, Slovenia, and Ukraine. Design and build the systems behind our AI assistant: agent flows, context retrieval, and the data connections that let it reason about live Kubernetes infrastructure. Build and evolve our public, permission-aware MCP server: curated tools, identity, audit, and strict safety gates, so customers can use CAST AI from their own AI clients. Develop and maintain cloud connectivity across AWS, GCP, and Azure, and the data foundations our agents build on. Write production Go services that interact with cloud provider APIs, the Kubernetes control plane, and LLM APIs in real time. Own features end-to-end: from design through implementation, testing, and production rollout (most projects ship in 1 to 4 weeks). Debug novel problems: an agent giving a wrong answer, a cross-cloud permission edge case, a data freshness issue that only appears at scale. Build the quality harness: evals, telemetry, feedback loops, that let us ship agent improvements without regressions. Contribute to product direction and backlog. Shape what gets built next, not just how it's built. Participate in the team's on-call rotation. Tools We Use Daily Programming Languages: Go AI & Agents: MCP (servers and clients), agent gateways, LLM provider APIs, RAG, evaluation pipelines Cloud & Orchestration: Kubernetes, AWS, GCP, Azure Infrastructure as Code: Terraform Databases & Storage: PostgreSQL, Cloud Object Storage, ClickHouse Workflows & APIs: Temporal, GCP Pub/Sub, gRPC, REST Observability & Product Analytics: Prometheus, Grafana, Loki, Tempo, PostHog CI/CD & GitOps: GitLab/GitHub CI with ArgoCD and Kargo