Summary
✨ AI‑Generated
A software engineering role focused on building AI agent platforms that automate repetitive workflows. This is a hands-on production engineering role involving real-world AI applications.
Highlights
Build production AI agents that automate complex workflows and create measurable business impact.
Description
A global media and content business is hiring an Software Engineer with strong AI knowledge to build the first dedicated agent platform inside a high-volume, deadline-driven editorial and licensing operation.
Editorial teams across four continents source, clear, produce and distribute content seven days a week to over 1,500 clients, sitting on an archive of roughly one million photographs and 40,000 video clips.
A lot of the work keeping that moving is repetitive and judgement-light and currently scales linearly with headcount.
This role exists to change that.
You'll be the first dedicated hire on the agent platform, building a suite of AI agents that take on those repetitive layers so editorial and commercial teams can focus on the work that actually needs a human.
This is a build role, not a research role, and success looks like agents running in production against real workflows, not prototypes.
Role: Software Engineer
Salary: Up to £55k (dependent on experience)
Location: Hybrid, Birmingham.
2 to 3 days on site
What you'll be doing:
Design, build and ship production LLM agents against real editorial, rights, archive and commercial workflows, from scoping through to deployment and monitoringBuild the shared platform underneath the agents including orchestration, tool and API integrations, retrieval, prompt management, evaluation and observabilityIntegrate agents with existing systems including the archive, submission portal, clips platform and internal editorial toolingWork directly with editorial, research and commercial teams to identify the workflows worth automating and define what 'good enough to trust' looks like for eachBuild evaluation and guardrails so agent output quality is measurable rather than anecdotal, with human review at the right pointsOwn cost and latency, keeping model spend proportionate to the work being replacedDocument and hand over so the platform is not a single-person dependencyKeep an eye on the tooling landscape and make pragmatic build-versus-buy calls
What you'll need:
3+ years commercial software engineering experience with strong TypeScript skills (and ideally a background in PHP)Experience with either Claude Code, Cursor or CodexBuilt and shipped at least one LLM-powered feature or agent into production and operated it afterwards (real, used side projects count)Practical grasp of the agent toolkit: function and tool calling, RAG, vector databases, structured output, prompt engineering and context managementComfortable with at least one agent framework or SDK, with an understanding of why the abstractions exist rather than blind loyalty to a specific oneSolid API and integration experience, since much of this role is plumbing agents into systems that were not designed for themAble to talk to non-technical colleagues about what an agent can and cannot reliably do, and confident enough to push back when a request is a bad fit
This role would suit an engineer who wants genuine greenfield ownership of an agent platform, a varied problem space spanning editorial, rights, archive and commercial, and short feedback loops with the people whose work the agents actually change.
