Location: Manchester, UK Please note: This role is based in Manchester and no visa sponsorship is available .
Learn more about the general tasks related to this opportunity below, as well as required skills.
Role Overview We are looking for an experienced AI Engineer to design, build, and scale advanced AI-driven systems.
You will play a key role across the full AI lifecycle, working with modern LLM frameworks, retrieval-augmented generation (RAG), and agentic workflows to deliver production-ready, business-critical solutions.
You'll collaborate closely with cross-functional teams, contribute to technical strategy, and support the growth of a high-performing engineering function.
Key Responsibilities Design, architect, and optimise AI-driven systems with a focus on scalability, performance, and reliability.
Implement vector and graph database solutions, including retrieval-augmented generation (RAG) architectures, for efficient information storage and retrieval.
Develop agentic reasoning workflows using frameworks such as LangChain or LlamaIndex.
Own the full AI lifecycle, including data ingestion, embedding, extraction, synthesis, prompt engineering, and workflow orchestration.
Deploy, monitor, and maintain AI models in Docker-based, containerised environments.
Work closely with stakeholders and cross-functional teams to ensure AI solutions align with business objectives and deliver measurable value.
Contribute to internal knowledge sharing and mentor junior engineers within the team.
Skills and Experience Required Strong experience with Python-based frameworks, including: FastAPI for API development Celery for background task management PostgreSQL for database solutions Hands-on experience with vector and graph databases and RAG-based architectures.
Experience working with agentic and orchestration frameworks such as LangChain or LlamaIndex.
Solid understanding of large language models (LLMs), embeddings, and prompt engineering techniques.
Highly Desirable Experience designing multi-agent systems or autonomous workflows.
Practical experience deploying containerised, cloud-native tools using Docker.
Experience with advanced retrieval-augmented generation techniques, including: TAG (Tool-Augmented Generation): Integrating external tools to enhance model capabilities.
CAG (Context-Aware Generation): Leveraging dynamic context to improve relevance and coherence.
GraphRAG (Graph-Augmented Retrieval-Augmented Generation): Using graph-based structures to enhance retrieval and reasoning.
Core Competencies Stakeholder Engagement: Works effectively with cross-functional teams to align AI capabilities with business goals and deliver meaningful outcomes.
Collaboration & Teamwork: Contributes to a growing engineering team, sharing knowledge and mentoring junior engineers.
Adaptability: Thrives in a fast-paced, evolving environment, adjusting approaches as tools, systems, and requirements change.
Continuous Improvement: Designs, optimises, monitors, and maintains AI systems to ensure long-term performance, scalability, and reliability.
Innovation: Develops and implements advanced AI architectures, including agentic workflows, vector and graph databases, and RAG techniques.
Resilience: Manages end-to-end AI delivery, from deployment through monitoring and maintenance, ensuring stability in production. xxuwjjq