Integration & AI Automation Engineer

A bit about us

Established in 1994, The Fragrance Shop is the UK’s leading independent fragrance retailer. Our aim is to make mainstream and luxury fragrances affordable and accessible to all. We showcase more than 130 fragrance brands in over 220 stores throughout the UK and online at  We are expanding and are looking for an Integration & AI Automation Engineer to join the team and be part of a growing and vibrant brand.

• Enjoy work-life balance with our flexible working scheme - including 15 work from home days a year, duvet days and the choice to flex your working hours.
• Vibrant state-of-the-art office, conveniently located in Trafford Park with great transport links and free onsite parking.
• No need to travel to the gym – we have one here for you! Take advantage of our free onsite gym facilities before/after work or even pop in at lunch time.
• Generous staff discounts on a wide range of fabulous fragrances.
• Excellent progression and development opportunities - work with teams who are passionate about what they do and develop your expertise within a creative and collaborative space.

We are seeking a highly skilled Integration & AI Automation Engineer to design, build, and maintain our next-generation integration layer. In this role, you will move beyond traditional point-to-point integration, leveraging n8n and advanced Large Language Models (LLMs) to build autonomous AI agents, intelligent workflows, and robust data pipelines. You will be responsible for connecting our core retail systems (eCommerce, ERP, OMS, and CRMs) with cutting-edge AI orchestration layers to drive operational efficiency, intelligent customer service resolutions, and real-time data automation.

• Architect, deploy, and optimize scalable, asynchronous workflows using n8n (self-hosted Cloud environments).
• Build advanced workflows utilizing n8n’s Advanced AI nodes, utilizing Lang Chain concepts, vector stores, and custom tool creation.
• Implement rigorous error handling, custom fallback routing, and alert mechanisms within n8n to ensure zero data loss across business-critical pipelines.
• Write custom JavaScript/Type Script snippets within data transformation nodes to handle complex payloads and data normalization.

• Integrate foundation models (OpenAI, Anthropic, open-source models) via API into live production workflows.
• Design, test, and version‑control complex system prompts, steering autonomous agents to operate reliably within strict enterprise guardrails.
• Implement Retrieval‑Augmented Generation (RAG) pipelines by connecting vector databases (e.g., Pinecone, Qdrant, Milvus) to supply AI agents with real‑time operational context.
• Build and maintain Human-in-the-Loop (HILA) approval layers to seamlessly route high‑uncertainty AI outputs to human operational queues (via Slack, Teams, or CRM webhooks).

• Develop custom, reusable n8n nodes or robust HTTP request architectures to interface with major retail enterprise platforms (e.g., Shopify Plus, Microsoft Business Central, Zendesk, or custom 3PL APIs).
• Ensure high-performance data syncing between real‑time webhooks, relational databases, and distributed event streams.
• Optimize API token usage, monitor latency, and implement intelligent rate‑limiting strategies to control third‑party LLM costs.

• n8n Mastery: Minimum 2+ years of hands‑on experience building complex production‑grade workflows in n8n. Deep understanding of sub‑workflows, merge strategies, wait states, and webhook handling.
• AI/LLM Execution: Proven track record of deploying LLMs into business processes. Experience with function‑calling/tool‑use paradigms where an LLM dynamically chooses to call backend APIs.
• Programming: Strong proficiency in Node.js / JavaScript / Type Script and/or Python
  .
• API Architecture: Deep expertise in RESTful APIs, webhooks, JSON data manipulation, authentication protocols (OAuth2, API Keys), and GraphQL.
• Dev Ops & Infrastructure: Solid understanding of hosting n8n securely (Docker, AWS, or similar…