AI Integration Engineer

About SimplyCubed

SimplyCubed is an AI automation business. We deliver custom AI agents trained on a customer's own data and wired into the tools they already run, live in 2 to 5 weeks rather than the six months and $50K+ an enterprise build demands. Our agents take over real, repetitive work across sales, support, and operations: qualifying leads, resolving tickets end to end, and moving data between systems like Slack, HubSpot, Intercom, Zendesk, and Notion. Every agent ships with scoped access, audit logging, and human-in-the-loop controls, a discipline that comes from our founder's background running security for finance and payments companies.

We run a productized model: a repeatable offering delivered the same disciplined way every time, not bespoke project work. We operate as a fully remote, global team of people, specialists, and agents. We value quality over volume, systems that improve themselves over time, and the kind of methodical thinking that catches a problem before it reaches a customer.

The role

We are building the internal agent systems that run our own business and power what we deliver to customers. An agent is only as capable as the tools it can reach, and this role owns that layer: the integrations agents call, the data that flows between systems, and the reliability and security contract they all run under.

You will build and maintain the connective tissue as production code, then keep it dependable as upstream APIs change and the surface grows. Where the Agent Skills Engineer role validates that an integration behaves, this role builds and owns it in production.

Work with us at the commitment that fits you, full-time, part-time, or per engagement, always as an independent partner and always fully remote.

What you'll do

• Build and register the MCP servers and tool integrations that give our agents their reach into the systems customers already run
• Own the data flow between systems like Slack, HubSpot, Intercom, Zendesk, and Notion: how records move, stay in sync, and reconcile when they drift
• Design and uphold the reliability contract for every integration: retries, idempotency, and graceful handling of partial failure, so a flaky upstream never corrupts state
• Own the security posture of the integration layer: scoped access, least privilege, audit logging, and careful handling of tokens and credentials
• Maintain integrations as production code: monitor them, fix them when an upstream API changes, and keep them dependable as the surface grows
• Work closely with the people who validate the skills built on top, so a problem is caught early and fixed at the right layer

Who you are

You come from a software engineering background and like owning the parts other people would rather not:

• A builder, not only a tester. You are comfortable writing and maintaining production integration code, not just reviewing or validating it.
• Fluent in the plumbing of integrations. You are strong on auth and OAuth, API keys, rate limits, token scopes, webhooks, and pagination, and you know where these things tend to break.
• Production TypeScript and/or Python. You can build in at least one of them to a real, shipping level, not just read it.
• Security-minded by default. You reach for least privilege and scoped access without being asked. It is the same discipline we apply to every agent we ship.

Nice to have

Direct experience with MCP, agent tool protocols, or LLM frameworks is a plus but not required. The integration fundamentals, auth, reliability, and security, matter more, and the agent-specific layer is learnable on the job. If you have it already, even better.

There is a defined growth path from this role toward Applied AI Engineer for people who want to move from owning the connective tissue to building whole agent workflows.

How we work

• Fully remote, asynchronous-friendly, global
• Direct collaboration with the founder, with real autonomy once direction is set
• Independent partners, not payroll staff, with the same investment in everyone
• Quality over count: a small set of solid, reliable integrations beats a large pile of fragile ones
• Clear documentation and SOPs as a core deliverable, not an afterthought

Where this role sits

This is one tier of a capability ladder that runs from validating what our agents depend on up to owning a whole customer outcome. We meet you at the tier that fits you now and grow with you as the work and your capability line up.

1. 1 Agent Skills Engineer Validate and harden the skills, tools, and integrations our agents rely on.
2. 2 AI Integration Engineer You are here Build and own the integration layer those agents run on.
3. 3 Applied AI Engineer Design, evaluate, and ship whole agent workflows in production.
4. 4 Forward Deployed Engineer Own a customer's outcome end to end, embedded in their context.

To apply

Tell us about an integration you built and kept running in production: what it connected, how you handled auth and failure, and something that broke that you had to fix. We care more about how you think than about a polished résumé.