About this role
Salary: £100,000 - 100,000 per year
Requirements: Strong software engineering fundamentals across clean code, testing, CI/CD and production systemsStrong programming skills in Python, TypeScript or similar, with experience across multiple modern languagesFull-stack capability, including back-end and data engineeringProven experience building and shipping production LLM/AI applicationsHands-on experience with RAG, AI agents, prompt engineering, tool orchestration and MCPExperience with AI evaluation, testing, datasets and guardrailsClient-facing experience and an understanding of enterprise security, compliance and legacy environmentsHigh autonomy, strong communication skills and a commercial, outcome-focused mindsetVector databases, embeddings or fine-tuningAWS or Google CloudStartup or founder experienceOpen-source contributions or AI side projects Responsibilities: Build AI solutions using RAG, AI agents, LLM integrations and MCPTake solutions from prototype through to production, including security, scalability, guardrails and observabilityBuild AI evaluation and testing frameworks to measure accuracy and reliabilityWork with complex client data, integrations and enterprise environmentsWork directly with clients, demo progress and iterate quickly based on feedbackDevelop the internal AI platform and reusable engineering acceleratorsHelp upskill client engineering teams and stay on top of emerging AI technologies Technologies: AIAI AgentsAWSCI/CDCloudFine-tuningLLMMCPPythonRAGSecurityTypeScript More:
We are a growing technology consultancy building an AI-native engineering capability. This is a permanent hybrid role based in Leeds, offering a salary of up to £100,000, private healthcare, professional development and funded learning, hybrid working with remote flexibility, and clear progression within a growing engineering function. You will work in a small delivery pod on modern, AI-enabled systems at scale, with ownership across discovery, architecture, build and production, and the opportunity to help shape our internal AI platform and reusable accelerators.
last updated 39 week of 2026