ABOUT CONTENTJET
ContentJet is a Canadian UGC creative agency that connects brands with creators to produce high-performing user-generated content at scale. We serve global clients across e-commerce, healthcare, and marketing verticals.
Our core belief: every manual, repetitive task inside an agency can and should be replaced by an AI agent or automation. We use Claude Code CLI, Claude Cowork with MCP connectors, OpenClaw, n8n, VAPI, and custom multi-agent systems to eliminate manual work across every layer of our operations — from creator sourcing and outreach to content production, team coordination, and client delivery.
THE MISSION: SHIELD OPERATIONS AND PERFECT THE AI DEPLOYMENTS
ContentJet is undergoing a massive transformation to become a fully AI-native agency. While our AI Agent Architect and Automation Engineer build the complex infrastructure, we need a ruthless tester and operational bridge.
Your mission is simple: ensure that no buggy agent, broken n8n workflow, or hallucinating AI ever reaches the CEO, our team, or our clients. You are the ultimate gatekeeper of quality and the translator between our agency operations and our engineering pod.
THE ROLE
You are the operational anchor of our AI transformation. You will not be writing the Python code or building the complex multi-agent architectures, but you must be technical enough to understand how they work, how they connect via APIs, and exactly how they break.
You will audit our existing manual operations, write clear documentation detailing exactly what the AI needs to do, and hand those requirements to the engineering team. Once they build an agent (deployed via OpenClaw ) or an automation (via n8n ), your job is to try to break it. You will test every edge case, log every bug, and manage the feedback loop until the system is bulletproof and ready for the agency floor.
WHAT YOU WILL DO
* Audit and Document: Deep-dive into our current agency operations, mapping out every manual click, copy-paste, and email to create clear requirements for the AI Architect.
* Relentless QA & Testing: Act as the\ "human-in-the-loop\" during the testing phase. You will vigorously test AI agents across Slack, Monday.Com, and web interfaces to find edge cases, hallucinations, and logic failures before deployment.
* Bug Reporting & Triage: Manage the development pipeline. When a VAPI voice agent fails a creator screening or an n8n webhook drops data, you write the detailed bug report for the engineering team.
* Prompt QA: Review the outputs of AI workflows (such as personalized creator briefs or automated emails) to ensure the tone, accuracy, and brand alignment are perfect.
* Protect the CEO: Fully own the testing and troubleshooting phase so the CEO can focus purely on running the agency, completely removed from software QA.
* Team Training: Once an AI agent or automation is finalized, you will write the standard operating procedures (SOPs) and train the ContentJet staff on how to use the new system.
MUST-HAVE SKILLS
* Exceptional QA Experience: You have a proven track record of testing complex software, automations, or AI workflows and documenting bugs clearly.
* Technical Literacy: While you aren't writing production Python, you understand how APIs work, what webhooks are, and the basics of n8n and LLM prompt logic. You know why systems break.
* Hyper-Organization: You are a master of project management tools (Monday.Com, Jira, Linear) and can manage multiple concurrent AI deployments without dropping the ball.
* UGC / Agency Understanding: You understand how a creative agency functions—what a creator brief is, how outreach works, and the level of quality clients expect.
* Flawless English Communication: You will be writing detailed technical tickets, testing client-facing AI outputs, and writing internal training guides.
NICE-TO-HAVE
* Previous experience working in an AI startup or working directly alongside AI Engineers.
* Hands-on experience with Monday.Com, n8n, or testing chatbot/agent outputs.
* Background in UGC, creator operations, or content production workflows.
* Aligned with North American time zones (EST/PST).
WHAT SUCCESS LOOKS LIKE
* Within 30 days: You have fully audited our top 5 manual workflows, created a clear roadmap for the engineering pod, and established a formalized bug-reporting and testing system.
* Within 60 days: You are rigorously testing the first wave of deployed AI agents. You have successfully caught, documented, and helped resolve critical edge cases before they impacted agency staff.
* Within 90 days: You completely own the AI product lifecycle. The CEO is entirely removed from all QA and troubleshooting, and manual work across the agency is rapidly decreasing thanks to your smooth deployments.