AI Engineer

This isn’t about building another chatbot or implementing a handful of AI automations.

The business wants to create its own internal “Second Brain” - a secure, intelligent AI platform that connects its existing systems, data, people and workflows through one central interface.

Imagine a platform where business leaders can ask questions about company performance, instruct AI to complete tasks, trigger existing automations and have specialist AI agents working collaboratively across departments.

The foundations are already there, with existing AI-powered workflows in operation. The next challenge is connecting everything together into one scalable, intelligent ecosystem.

We’re looking for someone who can take genuine ownership of the technical solution, from shaping the architecture and advising on the best approach through to hands-on development and delivery. What You’ll Be Doing

• Architecting and building a secure, scalable AI intelligence platform from the ground up.
• Designing agentic AI systems capable of understanding requests, orchestrating tasks and delegating work to specialist AI agents.
• Developing a central AI interface that allows users to interact with business data, systems and workflows through natural language.
• Integrating LLMs with existing business applications, ERP/CRM platforms, APIs, databases and automation tools.
• Building RAG capabilities to enable AI to securely retrieve and reason over internal company knowledge, documentation and operational data.
• Developing multi-agent orchestration, task routing and multi-intent processing capabilities.
• Connecting and enhancing existing automations rather than unnecessarily rebuilding working solutions.
• Implementing human-in-the-loop approvals, role-based permissions, audit trails and appropriate AI governance.
• Designing persistent memory, context management and secure knowledge retrieval.
• Establishing cloud infrastructure, deployment processes, monitoring and scalable architecture.
• Advising business stakeholders on technical feasibility, architecture, delivery priorities and the longer-term AI roadmap.

We’re particularly interested in speaking with experienced engineers or architects who have genuine hands-on experience building production AI systems, rather than solely experimenting with LLMs or developing proof-of-concept applications.

Ideally, you’ll bring experience across:

• LLMs & Agentic AI: Experience building applications using OpenAI, Anthropic Claude, AWS Bedrock or similar.
• AI Orchestration: LangGraph, LangChain, Strands Agents, Semantic Kernel, AutoGen or comparable frameworks.
• Backend Engineering: Strong Python development skills, ideally with FastAPI or similar frameworks.
• RAG & Knowledge Systems: Vector databases, embeddings, semantic search, document ingestion and retrieval architectures.
• APIs & Integrations: Experience connecting AI applications to existing enterprise systems, databases and third-party services.
• Cloud Architecture: AWS, Azure or GCP, with experience designing secure, scalable production environments.
• Automation & Workflows: Understanding of workflow orchestration, event-driven systems and tools such as Make, n8n or similar.
• AI Governance: Human-in-the-loop processes, authentication, access controls, observability, evaluation and secure AI deployment.

You don’t need experience with every framework listed. We’re much more interested in your ability to design robust solutions, understand how different technologies fit together and make sensible architectural decisions. The Person

This opportunity would suit someone who enjoys solving complex technical challenges and wants to play a significant role in shaping how AI is adopted across a business.

You’ll ideally be someone who:

• Has experience taking AI solutions from concept through to production.
• Can operate strategically while remaining genuinely hands-on.
• Understands the challenges of integrating AI into existing business systems.
• Can advise stakeholders, challenge assumptions and recommend practical solutions.
• Takes security, reliability, scalability and governance seriously.
• Enjoys working with autonomy and taking ownership of technical delivery.
• Can balance ambitious long-term AI capabilities with realistic, incremental delivery.