AI Automation Engineer

Ghalib Ashrafi; Northern (KY); Hybrid; USD 120,000 - 160,000; Full time

Benefits offered by this job

Tooling budget for AI

Paid learning time

Portfolio of work you keep

Limited client load

Job summary

Ghalib Ashrafi is hiring an AI Automation Engineer to build LLM-powered workflows for US client accounts, with a focus on reliability, scale, and compliance with state-by-state rules. The role operates remotely across US time zones and requires translating complex architecture to non-technical clients.

The candidate should have 3+ years of production LLM experience, strong Python or JavaScript skills, and a track record of delivering unattended automation in production environments.

Qualifications

• 3+ years building software with production LLM work.
• Comfortable with workflows that hold up at volume and across inconsistent state-level rules.
• Strong Python or JavaScript, comfortable with APIs, queues and webhooks.
• You have shipped something that ran unattended and dealt with it breaking.

Responsibilities

• Build LLM-powered workflows for client accounts in the US.
• Write evaluation sets that decide whether a workflow ships.
• Ensure workflows scale and handle state-by-state variations.
• Explain architecture to non-technical clients in their language.

Skills

LLM workflows

Python/JavaScript

APIs & webhooks

Queues

Production deployment

Tools

n8n

Make

Hand-written services

Job description

3. AI Automation Engineer| Open Role# AI Automation Engineer - United StatesBuild LLM-powered marketing workflows for US client accounts at volumes that break things, across rules that change state by state. You write the evals, and you carry the pager.Paid task, never free work · Feedback either way · 2-3 weeks end to endLocation**Remote - United States**The Role## About this jobThis is applied engineering, not research. The workflows you build run unattended on real client operations - lead qualification, content pipelines, reporting, WhatsApp triage - which means they have to handle messy input, fail safely, log everything and stay cheap to run. Almost everything is built inside the client's own accounts and API keys rather than ours, so the work has to be legible to somebody else afterwards. This role covers our US clients across time zones, which means overlap hours rather than an offshore handoff. It is the most competitive attention market we work in, accessibility exposure is a genuine legal risk rather than a nicety, and the rules change state by state.### What you'll do* Build LLM-powered workflows that survive contact with a real client account* Write the evaluation sets that decide whether a workflow ships at all* Build for scale first, because US client volumes break workflows that were fine everywhere else* Handle state-by-state variation in the data rather than assuming one national rule* Automate across three map surfaces and the aggregators behind them, not just the Google profile* Say when a workflow should not be automated, including when it costs us scope### What we're looking for* 3+ years building software, with real production LLM work among it* Comfortable with workflows that have to hold up at volume and across inconsistent state-level rules* Strong Python or JavaScript, comfortable with APIs, queues and webhooks* You have shipped something that ran unattended and dealt with it breaking* Able to explain your architecture to a non-technical client in their language* Able to work United States client hours from wherever you are based### Nice to have, not required* Experience with rate limits, retries and the unglamorous parts of running automation in production* Familiarity with n8n, Make or similar as well as hand-written services* Any marketing operations background at all - it is rarer than it should be### You'd probably be unhappy here if...* You want to do research or model training rather than applied delivery* You would rather not talk to clients about what you built* You believe most things should be fully autonomous on day one* You want the interesting build without the pager that comes after itWe put this on every job for the same reason we put it on every service page: finding out in month three costs us both far more than reading it now.* **The range, before the first call** - we tell you what the role pays before you spend time on it, we do not negotiate people down from it, and we will not ask what you currently earn.* **Remote - United States** - we ask for overlap hours with the team and your clients, not a chair.* **Paid learning time** - courses, conferences and certifications covered, with time in the week to use them.* **Your own tooling budget**, including AI tooling. Nobody here does a job badly because a licence was refused.* **A portfolio you keep** - with client permission, the work is yours to show.* **A capped client load** - we limit how many accounts we take on precisely so nobody carries twelve.Send us **something you have built** - a site, an audit, a campaign, a workflow, a piece of writing - along with a short note about why this role. A CV on its own tells us very little, and we would rather read one real thing than three pages of bullet points.Put **\"AI Automation Engineer\"** in the subject line. We read every application and we reply either way, usually with a reason. If we go quiet for more than a week, chase us - that is our failure, not yours.**No recruiters or agencies, please.** We hire directly and always have.