Agent Skills 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. This role owns the configuration, skill development, and validation layer of those systems.

You will be developing, testing, and refining the skills, workflows, and tool integrations that our agents rely on, then making sure they hold up under real use. Agents are only as good as the tools and skills you give them, and this role exists to make those tools dependable.

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

• Develop and refine agent skills (defined primarily in markdown) for tasks across outreach, scheduling, support, content generation, and internal operations
• Identify, test, and validate third-party tool integrations, both paid and free, and recommend the right fit for each workflow
• Validate and wire up the deterministic scaffolding agents depend on: calendar and scheduling, email, CRM sync (HubSpot), and Google Workspace integrations, treated as integration testing and verification rather than owning the production integration code
• Design test cases and edge cases for agent workflows, then verify skills behave reliably and fail safely
• Evaluate whether a skill genuinely improves over its learning loop versus simply reporting confidence, and apply healthy skepticism to an agent's self-assessment
• Curate the skill library over time: keep what works, merge overlap, archive what's stale
• Document skills, workflows, and standard operating procedures so the system stays repeatable as the team grows

Who you are

You come from a testing and automation background and bring the mindset that comes with it:

• Analytical and systematic thinking. You break complex workflows into parts, map how they connect, and find the edge cases other people miss.
• Systems thinking. You see how individual skills and tools fit into a larger whole, and you design the scaffolding so the whole holds under load.
• A tester's instinct for breakage. You are detail-oriented and rigorous, and you would rather find the failure yourself than have a customer find it.
• A genuine appetite for continuous self-improvement. You enjoy learning new tools and frameworks, and you treat your own skill set the way we treat our agents': always iterating.

Nice to have

Direct experience with AI agents, LLMs, or agent frameworks is a plus but not required. The systematic, methodical foundation matters more, and the AI-specific layer is learnable on the job. If you have it already, even better.

What we do ask is curiosity about AI tools and frameworks and a willingness to close the gap quickly. Prior software development experience is welcome but not the focus of this role; this is skill development and validation work, closer to testing than to building from scratch.

There is a defined growth path from this role toward AI Integration Engineer and, beyond it, Applied AI Engineer for people who want to move from validating the system to building it.

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 skills 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 You are here Validate and harden the skills, tools, and integrations our agents rely on.
2. 2 AI Integration Engineer 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 a system or workflow you tested or automated, what you found, and how you made it more reliable. We care more about how you think than about a polished résumé.