> Markdown version of [/jobs/ext/1202034-ai-agent-engineer](https://www.wearedevelopers.com/jobs/ext/1202034-ai-agent-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Agent Engineer - **Company:** Edge Tech - **Location:** UK - **Experience:** Expert - **Salary:** £180,000.0 - £220,000.0 - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Business Logic, Databases, Software Debugging, Blockchain, Software Engineering, TypeScript, Large Language Models, Prompt Engineering, Web3.js, Virtual Agents, Web Api - **Published:** July 8, 2026 - **Apply:** https://jobs.edgetech.ai/apply/36121/senior-ai-agent-engineer ## About the Role We need a senior engineer (5+ years) who has personally built and shipped a complete AI agent system in production - not a prototype, a demo, an internal tool, or a thin wrapper around an LLM API. You've owned the harness end-to-end: orchestration/planning, tool-calling, memory, retrieval/RAG, evaluation, and guardrails - with real users relying on what you shipped. Building only one slice, or agent work that never reached production, is not enough for this seat. You have a real software engineering foundation underneath - systems design, debugging, architectural judgment - and you're ready to operate at founding intensity. You'll ideally have: * 5+ years of software engineering experience with strong TypeScript proficiency. * Personally built and shipped a complete AI agent system in production, owning the full harness end-to-end (orchestration, tool-calling, memory, retrieval, evaluation, guardrails). * Experience with LLM orchestration, structured outputs, function calling, embeddings, and RAG. * Experience with prompt engineering and validation systems for reliable AI outputs. * Startup experience - bonus if early stage (founding team, first 10-20 engineers, or own startup) - operated without structure. * A technical undergraduate degree (CS, data science, or similar) from a top US university. * AI agent experience in a domain that transfers - reasoning over structured data, memory, orchestration, multi-step workflows, or accuracy-critical outputs. * Mastra framework experience is a strong plus. What We're Not Looking For Currently in an engineering manager role and no longer coding daily. AI agent experience confined to non-transferable domains with no other production agent work (e.g., blockchain/Web3, voice-AI/IVR). Experience focused solely on one slice of the agent harness without end-to-end ownership. ## Description * Designing, building, and shipping the agentic core using TypeScript/Bun with Mastra, turning structured financial data and customer context into reliable AI outputs. * Creating agentic systems that reason across structured financial data, business context, documents, and user instructions. * Developing robust tool-calling, planning, memory, retrieval, and orchestration layers for production AI agents. * Connecting agents to internal data sources, third-party APIs, databases, documents, and business logic. * Building guardrails, validation systems, and evaluation workflows to improve accuracy, reliability, and trustworthiness. * Working closely with product, engineering, and founders to turn complex financial use cases into intuitive AI-powered product experiences. ## Related Videos - [Kubernetes and Microservices with Multi-Model Databases](https://www.wearedevelopers.com/videos/382-kubernetes-and-microservices-with-multi-model-databases) - [Web APIs you might not know about](https://www.wearedevelopers.com/videos/281-web-apis-you-might-not-know-about) - [Smart Contract fundamentals - My first DApp](https://www.wearedevelopers.com/videos/52-smart-contract-fundamentals-my-first-dapp) - [On a Secret Mission: Developing AI Agents](https://www.wearedevelopers.com/videos/1510-on-a-secret-mission-developing-ai-agents) - [Fault Tolerance and Consistency at Scale: Harnessing the Power of Distributed SQL Databases](https://www.wearedevelopers.com/videos/1146-fault-tolerance-and-consistency-at-scale-harnessing-the-power-of-distributed-sql-databases) - [Project Fugu: Extending the web](https://www.wearedevelopers.com/videos/832-project-fugu-extending-the-web) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [From Prototype to Production: Build AI Agents with This Free 4-Course Learning Path](https://www.wearedevelopers.com/magazine/655-from-prototype-to-production-build-ai-agents-with-this-free-4-course-learning-path) - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care) - [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering)