Senior AI Automation Engineer (n8n Operations and Agentic Workflows)

Location: Warsaw, Poland / Kyiv, Ukraine / Remote
Format: Full-time
Contract: B2B
Seniority: Senior
English: B2+

About the role

In our new project, we operate an automation-first media publishing business with multiple newsletter brands across several verticals such as finance, geopolitics, wellness, and more, reaching 20M+ people. Our focus is building reliable, production-grade automation that reduces manual work, prevents operational mistakes, and scales smoothly.

This is a hands-on engineering role for someone who can take messy, high-volume operational workflows and turn them into stable, observable, and maintainable systems using n8n, APIs, and AI.

What you’ll work on (core focus areas):
1) QA Automation Workflow with Agentic AI / similar tools (pre-send / pre-publish gates)

Design and maintain automated QA workflows that detect and flag high-impact issues in email newsletters before content goes out.

Examples:

• broken links and missing images
• duplicated blocks/paragraphs
• malformed HTML / broken elements
• rendering/layout anomalies across common email clients

The system should output a clear PASS/FAIL verdict, with severity levels and actionable notes, and route only flagged cases to human QA. 
 

2) Support Inbox Automation (triage + safe auto-actions)

Build and maintain automation that reduces support workload.

Examples:

• classifying inbound messages across hundreds of email accounts (platform requests, compliance/complaints, unsubscribe requests, etc.)
• triggering safe automated actions where appropriate (e.g., routing, logging, suppression/unsubscribe flows)
• labeling priority and urgency, and notifying a human support agent when needed
   

3) Content Automation Workflows (later phase, after ops stability)

As the system stabilizes, you’ll also contribute to AI-driven content workflows.

Examples:

• structured topic ingestion and enrichment (signals → multi-model brief → post)
• guardrails and quality gates (structured outputs, validation, retries)
• operational tooling that helps publishing teams move faster with fewer errors
   

4) Continuous improvement of our automation stack

Bring new ideas, scale, improve, monitor, and maintain the automation systems that power our AI-first media operations.
 

Key Responsibilities

• Design and implement advanced AI-driven workflows for QA, support operations, and content production.
• Automate repetitive, high-volume processes using AI tools, scripts, and integrations.
• Build systems connecting platforms via APIs, webhooks, and structured data pipelines.
• Reduce manual work, execution time, and error rates across teams through reliable automation.
• Implement guardrails for agentic flows: structured JSON outputs, validation rules, confidence thresholds, retries, and fallbacks.
• Own workflow reliability: monitoring, alerting, incident response, and runbooks.
• Document workflows clearly so they can be operated and extended by others.
   

Tech environment (examples, not a limitation)

We currently use tools like:

• n8n (workflow orchestration)
• Browser automation (e.g., Playwright or equivalent) where needed
• LLM/Vision models (Gemini/OpenAI/Claude or equivalents)
• Email testing / preview tools (e.g., Email on Acid / Litmus; plus MailerCheck/Mailtrap or equivalents)

You’ll have the autonomy to propose better tooling and architectures if they improve reliability, speed, or quality.
 

Requirements

• 4-6+ years of experience in automation engineering / technical operations / integration engineering / workflow engineering (including AI workflow automation and agentic systems)
• Proven experience building production workflows in n8n (or comparable platforms) with strong operational discipline
• Strong scripting skills in Python and/or Node.js (parsing, checks, utilities, integrations)
• Solid API integration skills (REST, webhooks, auth, pagination, rate limits)
• Working knowledge of PostgreSQL; familiarity with Supabase and Redis is a plus
• Practical experience using LLMs in production (structured outputs, evaluations/guardrails, prompt reliability) 
• Solid AIOps / MLOps / DevOps-style experience with major cloud/VPS providers (AWS, Google Cloud, DigitalOcean, Hetzner, etc.)
• Strong troubleshooting mindset: you can debug, stabilize, and keep systems running under load
• Ability to translate real operational needs into clean systems (not just prototypes)
• English B2+
   

Nice to have

• LangGraph experience
• Experience with email/newsletter workflows in tools like Substack, Ghost, Beehiiv, or similar
• Experience with support triage automation and SLA-based ops
• Familiarity with observability practices (logging, metrics, alerts)
• Background in media/publishing, performance marketing, or high-volume content operations