At a Glance
- Tasks: Build and maintain AI-powered tools, integrating large language models into workflows.
- Company: Trtl is a Glasgow-based travel accessories brand with over two million customers worldwide.
- Benefits: Enjoy hybrid working, 33 days annual leave, and opportunities for personal development.
- Other info: Work closely with marketing, operations, customer support, and finance teams.
- Why this job: Join a fast-growing company aiming to scale to £50M+ with AI at its core.
- Qualifications: Proficient in JavaScript/TypeScript, Java, and Python; strong understanding of LLM prompting.
The predicted salary is between 70000 - 90000 £ per year.
About Trtl
Trtl is a travel accessories brand based in Glasgow City Centre, Scotland. With over two million customers worldwide, we make travel easier — starting with our hero product, the Trtl Travel Pillow, reinvented from the ground up to solve a problem no one had properly fixed. We are a small, ambitious company that punches well above its weight — around £30M in annual revenue, selling across Amazon, Shopify/DTC, and TikTok Shop in the UK, US, and internationally. We have a clear ambition to scale to £50M+ and AI is central to how we get there. We have been building AI-powered tools and workflows into the business for two years. AI is already core to how we operate. This role exists to accelerate that — materially and measurably.
About the Role
We are looking for a Mid-Level AI Software Engineer — someone with strong software development foundations and growing hands-on experience with agentic AI systems. You will work directly within our technology team, reporting to our Head of AI. You will help build, extend, and maintain a growing ecosystem of AI-powered tools and integrations already live across the business — working closely with colleagues in marketing, operations, customer support, and finance to turn real problems into working solutions. We do not expect you to have shipped production-grade agentic systems at scale. We do expect you to understand how they work, to have built with LLMs in earnest — whether in a commercial setting or your own projects — and to be ready to grow fast in an environment that takes this seriously. If you want to learn what AI-native commerce looks like in practice and have the engineering foundations to contribute from day one, this role is for you.
What You Will Do
- Build & Maintain AI-Powered Tools
- Extend our existing suite: Take ownership of live AI tools and agentic workflows. Maintain and improve them as the business evolves.
- Ship new solutions: Design and build new AI-powered tools end-to-end.
- Integrate AI models: Work with large language models to power tools — classification, summarisation, structured generation, and decision support. We use Claude (Anthropic) as our primary model.
- Contribute to agentic systems: Help build and extend agentic workflows where AI takes actions, calls tools, and operates with varying degrees of autonomy.
- Software Development
- Write production code: This is a developer role. Clean, maintainable code that other people can rely on.
- APIs and integrations: Build and consume APIs, connect to third-party services, and ensure data flows reliably between systems.
- Infrastructure: Deploy and manage tools in cloud environments with proper scheduling, monitoring, and error handling.
- Collaboration & Problem Solving
- Work cross-functionally: Sit with colleagues across the business to understand their pain points. Translate vague problems into concrete, buildable solutions.
- Communicate clearly: You will regularly work with non-technical colleagues, being able to translate business requirements into technical solutions is important.
What We Are Looking For
- Core Engineering
- Proficient in at least two of JavaScript/TypeScript, Java, and Python — and comfortable picking up the third.
- Comfortable with infrastructure-as-code and CI/CD pipelines.
- Solid Git workflow and GitHub practices: PRs, branching, code review.
- AI & Agentic Systems
- Strong practical understanding of LLM prompting: system prompt design, chain-of-thought, structured outputs, prompt versioning.
- Working knowledge of MCP (Model Context Protocol) — ideally you have built or consumed MCP servers and understand the client/server model and tool schema design.
- Aware of common failure modes in agentic systems: prompt injection, tool misuse, hallucinated tool calls, context window limits.
- Ways of Working
- Self-directed: able to pick up an unfamiliar codebase, form a mental model of it, and start contributing without step-by-step guidance.
- Pragmatic about scope: ships working solutions rather than waiting for perfect ones.
Nice to Have
- Experience building and maintaining microservices architectures, including inter-service communication, data pipeline design, and API integration.
- Hands-on experience building agentic AI systems — not just calling LLM APIs, but designing multi-step agents, handling tool use, managing context, and reasoning about failure modes. Personal projects count.
- Exposure to LangChain, LangGraph, or similar orchestration frameworks.
- Understanding of RAG patterns and vector store integrations.
- Familiarity with e-commerce platforms: Amazon (Seller/Vendor Central), Shopify, or TikTok Shop.
What We Offer
- Hybrid working — 3 days per week in our Glasgow City Centre office.
- 33 days annual leave with option to buy more.
- Commitment to personal and team development.
- Social and wellbeing activities.
- Real ownership of AI work at a fast-growing brand — with commercial stakes and the autonomy to deliver.
AI Software Engineer in Glasgow employer: Trtl
Trtl, located in Glasgow City Centre, offers a hybrid work model and 33 days of annual leave. The team is dedicated to personal and team development, ensuring employees have real ownership of their AI projects.
