AI Engineer - Front end

Job Description

Build and operate the interface, semantic layer and controls that let AI agents work inside IFS software safely.  

This role is hybrid or remote.  

The role: 

You will own the web client of an AI agent product for our enterprise customers. It is a React and TypeScript single-page application, and almost everything on its screen arrives as a stream from a language-model agent.  

What you will do: 

• Build an interface that people can trust while the content on it is still arriving, changing and occasionally wrong.
• Turn what the agent produces into a usable interface: prose, generated views and actions the user can take.  
• Make sure the agent acts only with the user's explicit consent, and that people can always see what it did and why.  
• Own the front-end architecture, the component system and the contracts with the teams behind the agent. 
• Help move the interface towards Lit and Web Components, so that what we build is standards-based and not tied to a single framework or application.  
• Treat accessibility, performance, testing and observability as part of the product rather than a late pass.  
• Work across the boundary into the services your interface depends on, then ship what you build and run it in production.  

Why it is interesting:  

Most front-end work assumes that a page loads and is then correct. Here the content arrives in pieces, gets revised, sometimes fails partway and is sometimes wrong. And some of it is code a model wrote, which the browser should not trust. The protocols involved are young and still changing (AG-UI, A2UI, MCP Apps). You will help shape them, not just consume them.  

What we are looking for: 

• Substantial production single-page applications, built and operated, with real depth in TypeScript and React.  
• Asynchronous state you can reason about.  
• Browser security as a working concern: iframe sandboxing, postMessage, Content Security Policy, sanitising content you did not write.  
• Component and design-system work in a shared codebase, including web components used inside React.  
• Accessibility as a practice. You know how to keep it tested.  
• Willing to write Go and to read Python. Prior experience in either is not required.  
• Test-first habits and continuous delivery.  
• Clear writing. Decisions are recorded as short architecture decision records (ADRs), and protocols are documented before they change.  
• Comfortable working with AI coding agents as part of how you build.  

Also valuable: 

• A product surface built on a language model in production: streaming, partial output, retries, and showing uncertainty.  
• Hands-on knowledge of the Model Context Protocol (MCP) and MCP Apps, AG-UI or A2UI.  
• Experience building with Lit and Web Components, including shadow DOM and custom elements used from other frameworks.  
• Expression languages or compilers.  
• A platform where behaviour is configured through data or metadata rather than written in code.  
• Data visualisation.  
• Familiarity with Docker, Kubernetes and Helm.  
• Knowledge of an enterprise domain: asset management, field service, manufacturing, supply chain.  

Qualifications

• Production experience building and operating substantial single-page applications, with real depth in modern TypeScript and a current framework such as Angular or React. 

• Built a product surface on top of a language model in production: streaming, partial output, cancellation, retries, and what to show when the system is uncertain. 

• Component architecture and design-system work in a codebase other teams contribute to. 

• Accessibility as a working practice, and performance work you can describe in numbers. 

• Comfortable across the boundary: you can write the service-side code your surface needs. 

• Automated testing, observability and continuous delivery as part of how you build. 

Also valuable 

• A platform where behaviour is configured through data or metadata rather than written in code. 

• Mobile or progressive web applications, including offline behaviour and poor connectivity. 

• Voice interfaces. 

• Enterprise software domains: asset management, field service, manufacturing, supply chain. 

Additional Information

We believe that coming together as a community, in person, is important for innovation, connection and fostering a sense of belonging. Our roles have the right balance of remote and in-office working to enable flexibility for managing your life along with ensuring a real connection with your colleagues and the broader IFS community.