Bilingual AI Development Assistant

Merit Manufacturing; Colombia; On-site; COP 6,000,000 - 12,000,000; Full time

Job summary

Merit Manufacturing is seeking a proactive AI operations specialist to own the human-in-the-loop workflow for our internal platform used daily by production, warehouse, and shipping teams; you translate vague bug reports into scoped tickets with reproducible steps and guide AI agents to deliver tested fixes.

You will draft prompts, summarize changes, write documentation, and ensure that every change is traceable, aligned with user needs, and keeps the platform stable as it evolves.

Responsibilities

• Turn vague bug reports into scoped tickets with reproducible steps, and guide AI agents to deliver tested fixes.
• Draft prompts, summarize changes, and write documentation to ensure traceability and quality of outcomes.

Job description

We run an internal operations platform that a mid-sized manufacturer depends on daily — production scheduling, warehouse transfers, inventory counts, PO tracking, packout, and shipping. About fifty people use it, including floor staff on scan guns. It connects to an ERP and a Postgres database, and it changes almost daily.

Most of the code is written by AI coding agents. That part works. The bottleneck is the human loop around them: intake, triage, scoping, prompt-writing, reviewing what the agent produced, verifying it works, and keeping the documents agents read from current.

That loop is this job. You're not the developer. You're the person who turns "this button's broken" into a scoped, verified, shipped fix — agents do the building, your judgment makes sure it's right.

And you don't do it alone. You'll use AI to manage the AI — to draft prompts, explain a diff you can't read, summarize what changed, check an agent's work against what was actually asked for, and write up documentation. Knowing how to put a model to work on your own behalf is the core skill here.

What you'll do

About the role

We run an internal operations platform that a mid-sized manufacturer depends on daily — production scheduling, warehouse transfers, inventory counts, PO tracking, packout, and shipping. About fifty people use it, including floor staff on scan guns. It connects to an ERP and a Postgres database, and it changes almost daily.

Most of the code is written by AI coding agents. That part works. The bottleneck is the human loop around them: intake, triage, scoping, prompt-writing, reviewing what the agent produced, verifying it works, and keeping the documents agents read from current.

That loop is this job. You're not the developer. You're the person who turns "this button's broken" into a scoped, verified, shipped fix — agents do the building, your judgment makes sure it's right.

And you don't do it alone. You'll use AI to manage the AI — to draft prompts, explain a diff you can't read, summarize what changed, check an agent's work against what was actually asked for, and write up documentation. Knowing how to put a model to work on your own behalf is the core skill here.

Intake and triage. Turn vague bug reports from across the business into tickets with a repro path and a sample record.