AI Frontend Engineer in London

We are seeking a Frontend Engineer to join our Group Data team, working as part of the AI Agent Hub delivery team. This role will help build, extend, and improve the user experience for ITV's emerging internal AI platform, with an initial primary focus on Open WebUI, Svelte, TypeScript, TailwindCSS, reusable component architecture, and AI-specific interaction patterns.

You will work closely with platform, backend, product, design, architecture, cyber security, and data colleagues to create a secure, intuitive, and maintainable interface for ITV teams to use foundational models, assistants, agents, multimodal tools, and internal system integrations through a single governed experience.

The AI Agent Hub is a secure, governed internal platform that enables ITV teams to explore, build, and use AI assistants, agents, multimodal tools, and workflow integrations through a unified user experience. It is intended to reduce fragmentation in AI tooling, improve governance and observability, and make it easier for teams to experiment safely and deliver value using shared platform capabilities.

As a Frontend Engineer embedded into the Agent Hub delivery team, you will work day to day with software engineers, platform engineers, product, design, architecture, cyber security, and data colleagues to design and deliver the user-facing product layer of the platform. You will help make complex capabilities such as LLM routing, prompt configuration, role-based access, knowledge retrieval, tool calling, evaluation feedback, and usage analytics understandable and useful to ITV employees.

This role is positioned initially as a stream-aligned team role embedded in delivery. As ITV's AI platform model evolves through 2026, there is a clear opportunity for the role to develop toward a more Forward Deployed Engineer style in 2027 and beyond, helping other teams adopt the platform, shaping integrations, and contributing to an enabling team capability within a broader core platform model.

What you will do:

• Build and improve front-end features for the AI Agent Hub, primarily using Open WebUI, Svelte, TypeScript, and TailwindCSS.
• Refactor and maintain reusable Svelte components so the product remains consistent, accessible, performant, and easy to extend.
• Build high-quality streaming experiences for LLM interactions, partial response rendering, loading states, cancellation, retry, error handling, and fallback messaging.
• Work closely with backend and platform engineers to align UI features with API design, authentication flows, observability, deployment patterns, and operational support needs.
• Help manage ITV's Open WebUI customisations, including pragmatic fork and upstream management, upgrade planning, dependency hygiene, and maintainable extension patterns.
• Run, debug, test, and release the application using local development tooling, Docker and Docker Compose, automated testing, pull requests, and clear support documentation.
• Contribute to front-end test coverage using appropriate tools such as Vitest, Cypress, Playwright, or equivalent frameworks.
• Build product features that support responsible AI use, including feedback capture, evaluation hooks, audit views, provenance indicators, and human-in-the-loop review patterns.
• Help shape interfaces for internal system integrations, including APIs, knowledge sources, workflow automation, RAG pipelines, tool calling, and MCP-based capabilities.
• Over time, support wider AI platform adoption across ITV by helping teams configure assistants, connect tools, expose internal systems safely, and embed AI capabilities into their existing workflows.

Skills you’ll need (minimum criteria):

• Experience building production web user interfaces, ideally with 3+ years of applied front-end engineering experience.
• Strong Svelte or SvelteKit capability, or strong experience in another modern component framework such as React or Vue with a clear willingness to ramp quickly into Svelte.
• Strong TypeScript skills, including component design, state management, typed API integration, maintainable front-end architecture, and debugging complex UI behaviour.
• Practical understanding of LLM-powered product experiences, including streaming latency, prompt and system context, model selection, context windows, temperature, token usage, error handling, and fallback behaviour.
• Experience integrating with LLM APIs or OpenAI-compatible endpoints, or a strong interest in learning how these patterns work in a governed enterprise platform.
• Good understanding of security and privacy fundamentals for internal tools, including authentication, authorisation, session handling, role-based access control, and safe handling of user data.
• Strong product sense and communication skills and the ability to explain trade-offs clearly, collaborate constructively, and contribute to technical discussions across product, design, engineering, architecture, cyber security, and data.
• Ability to work closely with backend engineers to shape API contracts, troubleshoot integration issues, and deliver coherent end-to-end product features.
• Strong SDLC explore user experiences beyond chat, including IDE configuration, CLI agents, MCP servers, pull request review agents, CI/CD pipeline agents, and developer experience tooling.

Other things we’re looking for (key criteria):

• Experience contributing to design systems, accessibility standards, usability research, or developer experience improvements in internal platforms.
• Experience with, or interest in, customising and contributing to Open WebUI (Svelte, TailwindCSS, Python) or a similar open-source chat, assistant, or AI workspace interface.
• Experience with LiteLLM or similar LLM gateways, including model routing, virtual keys, budget controls, cost tracking, model aliases, retries, and fallback chains.
• Experience with Python, FastAPI, Node.js, or similar backend technologies sufficient to build or extend integration endpoints, API adapters, and lightweight platform services.
• Experience with Kubernetes, GitHub Actions, CI/CD pipelines, environment management, and production deployment workflows.
• Experience with observability for product and platform behaviour, ideally including OpenTelemetry, Prometheus, Grafana, structured logs, traces, and usage or cost dashboards.
• Familiarity with RAG pipelines, embeddings, vector stores such as Chroma, Qdrant, Postgres pgvector, or S3 vector, and UX patterns for citations, knowledge selection, and retrieval confidence.

Areas you may grow into:

• Familiarity with tool calling, function calling, agent configuration, agent lifecycle management, and human-in-the-loop review patterns.
• Building MCP servers or integrations that expose internal ITV systems, APIs, knowledge bases and developer tools to AI clients.
• Using developer code review agents and AI workflows such as GitHub Copilot, Claude Code, OpenCode or similar IDE and CLI-based tools.
• Understanding of VS Code extension configuration, LSP concepts, or the way IDE tools can be configured to package organisation-specific context into engineering workflows.
• Exposure to agent frameworks such as LangChain, LangGraph, Google Gemini Enterprise Platform (Vertex AI) Agent Engine, or Bedrock Agents, CrewAI, Mastra, smolagent, LlamaIndex.
• Exposure to semantic code search, RAG over source code.
• Conceptual understanding of agent memory architecture, including short-term context, long-term memory, persistence, decay, retrieval, privacy, and when memory should be avoided.
• Gain experience with SSO and enterprise access patterns, ideally OIDC, OAuth2, SAML, Okta, Amazon Cognito, JWTs and RBAC for internal tools.

Why this role is exciting:

This is an opportunity to help shape the product experience for a new internal AI platform at an early stage, with meaningful influence over how ITV employees discover, use, configure, and trust AI assistants and agents. You will work in a high-priority area at the intersection of front-end engineering, AI, product design, governance, and internal platform delivery. The role offers the chance to turn complex AI platform capabilities into simple, secure, and useful experiences for teams across ITV. It is also a role with visible progression potential. In the near term, the focus is on being part of a stream-aligned team delivering the AI Agent Hub. As the platform matures, there is a path toward broader enabling and forward-deployed engineering work, helping more teams adopt common AI capabilities and supporting applied AI use cases in both business and engineering workflows.