Senior AI Platform Engineer — Kubernetes & Cloud Agents

Creandum; New Jersey; On-site; USD 81,000 - 112,000; Full time

Benefits offered by this job

Competitive salary

Equity options

Remote-first environment

Fast-moving projects

Learning budget

Hackathons

Team events

Equipment budget

Flexible work

Job summary

CAST AI seeks a platform engineer to make AI-assisted Kubernetes conversations reliable, secure, and scalable. You will design and build the backend systems behind our AI assistant, focusing on agent flows, context retrieval, and live cluster reasoning.

You will own the MCP server and cloud connectivity across AWS, GCP, and Azure, writing production Go services that interact with cloud APIs and the Kubernetes control plane, with strong emphasis on safety, observability, and end-to-end delivery.

Qualifications

• Strong software engineering fundamentals and a generalist mindset.
• Production Go experience preferred or strong systems programming in a comparable language.
• Experience building/operating large-scale SaaS platforms.
• Solid understanding of Kubernetes and related concepts.
• End-to-end project ownership with delivery responsibility.
• Hands-on experience with AI coding agents and agentic workflows.
• Observability tooling in production.
• CI/CD and DevOps practices experience.
• Strong English skills, both verbal and written.
• Startup mindset: adaptable and proactive in ambiguity.

Responsibilities

• Design and build the systems behind our AI assistant: agent flows, context retrieval, and live Kubernetes data connections.
• Develop and evolve our public, permission-aware MCP server with identity, audit, and safety gates.
• Maintain cloud connectivity across AWS, GCP, and Azure and the data foundations agents rely on.
• Write production Go services interacting with cloud provider APIs, Kubernetes, and LLM APIs in real time.
• Own features end-to-end from design to production deployment (projects ship in 1–4 weeks).
• Debug novel production issues such as incorrect agent answers and cross-cloud permission edge cases.
• Build the quality harness: evals, telemetry, feedback loops to ship safely.
• Contribute to product direction and backlog; participate in on-call rotations.

Skills

Go programming

Kubernetes

Distributed systems

Auth design

Agentic development

Observability tooling

DevOps practices

English skills

Startup mindset

Tools

Terraform

PostgreSQL

GKE

AWS

GCP

Azure

GitLab CI

ArgoCD

Kargo

gRPC

REST

Job description

CAST AI seeks a platform engineer to make AI-assisted Kubernetes conversations reliable, secure, and scalable. You will design and build the backend systems behind our AI assistant, focusing on agent flows, context retrieval, and live cluster reasoning.

You will own the MCP server and cloud connectivity across AWS, GCP, and Azure, writing production Go services that interact with cloud APIs and the Kubernetes control plane, with strong emphasis on safety, observability, and end-to-end delivery.