AI Developer

Company
We’re recruiting for an established, high-growth consumer technology business in the North East that has developed a successful app-based product used by a substantial customer base.

Technology sits at the heart of the organisation, with established iOS, Android and backend engineering teams alongside a growing data capability. The business is investing further in its Newcastle technology hub and wants to build more of its critical technical capability in-house.

This is an environment where engineers can have genuine influence. You won’t be joining a huge AI department with narrowly defined responsibilities. You’ll have the opportunity to shape how AI becomes part of a live digital product and work alongside an established engineering function.

The role will operate on a hybrid basis, typically 2–3 days per week in the office, providing the opportunity to work closely with the wider engineering and product teams while retaining flexibility.

Role
This is first and foremost a development role.

We’re looking for an experienced AI Developer / Engineer who wants to design, build and ship production AI functionality, rather than someone whose background is predominantly AI strategy, policy or governance.

One of the first major challenges will be taking technical ownership of an AI-enabled meal-planning capability within an existing consumer application. The ambition is to create an intelligent user experience where customers can provide information such as available ingredients and nutritional requirements and receive useful, personalised meal suggestions without needing to leave the application.

You’ll determine how best to combine LLMs, application logic, rules-based systems and existing product data to create something that is accurate, scalable and commercially viable. A key challenge will be deciding when an LLM genuinely adds value and when deterministic logic or existing data provides a better answer.

You’ll be responsible for areas including:

• Designing and developing production-grade LLM-powered features and applications
• Building AI agents, conversational experiences and intelligent workflows
• Working with technologies such as AWS Bedrock, agent frameworks and MCP
• Integrating LLM capabilities into existing applications, APIs and datasets
• Designing hybrid solutions combining AI, rules-based logic and proprietary data
• Prototyping ideas quickly, testing them and taking successful concepts through to production
• Optimising prompts, context, model selection and architecture to improve latency, quality and cost
• Understanding and controlling token consumption and inference costs
• Evaluating new models, tooling and approaches as the AI landscape develops
• Working closely with backend, mobile, product and data colleagues to embed AI into the wider product
• Helping existing software engineers develop their understanding of practical AI engineering.

You’ll also become an internal technical authority on AI. There will therefore be an element of establishing sensible engineering standards and guardrails around how AI tooling is used, but this is not an AI governance role. The emphasis is firmly on engineering, experimentation and delivery.

This is an opportunity to move beyond proofs of concept and ChatGPT wrappers and tackle the much more interesting question:
How do you engineer AI into a real product, at scale, in a way that delivers measurable value to the customer?
Person
We’re interested in speaking with strong software engineers who have moved deeply into AI development, as well as established AI / ML Engineers with demonstrable experience building real-world applications.
You’re likely to have practical experience across several of the following:

• Large Language Models and Generative AI
• Building production applications using commercial or open-source LLMs
• AI agents and agentic architectures
• AWS Bedrock or comparable cloud AI platforms
• MCP / tool-enabled LLM applications
• Building chatbots or conversational applications
• API and application integration
• Prompt and context engineering
• Retrieval and grounding techniques
• Model evaluation and optimisation
• Token usage and AI cost optimisation
• Software engineering practices required to turn AI prototypes into reliable production systems

Importantly, we’re not looking for someone who has simply experimented with AI tools.
We want somebody who understands the engineering underneath them. Someone capable of looking at a problem and deciding what should be AI, what should be conventional software, what should be rules-based and how those elements should work together.

You’ll also need to be comfortable being the initial AI specialist in a wider engineering organisation. You should enjoy sharing knowledge, challenging assumptions and explaining complicated AI concepts in straightforward commercial terms. The role will sit alongside established engineering leads and provide AI expertise across the broader development function.

Above all, this role suits someone who likes building things.
If your idea of an interesting AI role is experimenting with new technology on Monday, writing code on Tuesday and seeing something you've built appearing in a real customer product further down the line, there is a lot here to get excited about.