Software Engineer

Digital Waffle; Birmingham; Hybride; GBP 65 000 - 90 000; Plein temps

Résumé du poste

Digital Waffle is hiring a Software Engineer to build a first-of-its-kind agent platform for a high-volume editorial and licensing operation. You will design, implement, and deploy production-grade LLM agents that automate repetitive workflows, integrating with archives, portals, and internal tools.

You will work in a hybrid setup in Birmingham, collaborating with editorial and commercial teams to push automation from prototype to trusted production within a fast-paced environment.

Qualifications

• 3+ years commercial software engineering experience with TypeScript
• Experience with Claude Code, Cursor or Codex
• Built and shipped at least one LLM-powered feature or agent into production
• Practical grasp of agent toolkit: function and tool calling, RAG, vector databases, structured output, prompt engineering
• Strong API and integration experience with existing systems

Responsabilités

• Design, build and ship production LLM agents against real workflows
• Build the shared platform underneath the agents including orchestration, tool and API integrations
• Integrate agents with existing systems such as archive, submission portal and editorial tooling
• Collaborate with editorial, research and commercial teams to identify automations
• Develop evaluation and guardrails so agent output is measurable with human review points
• Own cost and latency, keeping model spend proportionate to work
• Document and hand over so the platform is maintainable
• Monitor tooling landscape and make build-versus-buy decisions

Connaissances

TypeScript

PHP

LLM agents

API integration

Outils

Claude Code

Cursor

Codex

Description du poste

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

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 monitoring
• Build the shared platform underneath the agents including orchestration, tool and API integrations, retrieval, prompt management, evaluation and observability
• Integrate agents with existing systems including the archive, submission portal, clips platform and internal editorial tooling
• Work directly with editorial, research and commercial teams to identify the workflows worth automating and define what 'good enough to trust' looks like for each
• Build evaluation and guardrails so agent output quality is measurable rather than anecdotal, with human review at the right points
• Own cost and latency, keeping model spend proportionate to the work being replaced
• Document and hand over so the platform is not a single-person dependency
• Keep 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 Codex
• Built 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 management
• Comfortable with at least one agent framework or SDK, with an understanding of why the abstractions exist rather than blind loyalty to a specific one
• Solid API and integration experience, since much of this role is plumbing agents into systems that were not designed for them
• Able 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.