About the role:
Ready to build production AI that actually ships — not another proof-of-concept chatbot? Join us as a Senior Python AI Engineer on HR Expert, where you'll help design and build a modern, AI-enabled application from the inside out. This is a genuinely hands-on engineering role at the cutting edge of generative AI, agentic systems and Retrieval-Augmented Generation (RAG) — solving the hard, interesting problems around AI orchestration, information retrieval and grounding that most engineers only get to read about.
Responsibilities:
•Design, develop and maintain AI-powered application services using Python.
•Build and evolve agentic workflows and AI orchestration using LangGraph and LangChain.
•Develop scalable APIs and backend services using FastAPI.
•Design and implement Retrieval-Augmented Generation (RAG) pipelines that combine LLMs with enterprise knowledge and data sources.
•Work on retrieval strategies including vector, metadata and graph-based retrieval.
•Contribute to the architecture and implementation of complex AI workflows involving multiple agents, tools and data sources.
•Integrate AI services with the wider HR Expert application and existing enterprise systems.
•Develop and deploy solutions using Microsoft Azure, working across relational, document, vector and graph-based data stores.
•Collaborate with architects, developers, product owners and other technical specialists to turn requirements into robust technical solutions.
•Participate in technical design discussions, code reviews and engineering decision-making.
•Help establish good engineering practices around testing, observability, performance and maintainability of AI applications.
•Investigate emerging AI technologies and evaluate where they can provide practical value to the product.
•Occasionally contribute to frontend or existing .NET services where needed — though this is not the primary focus of the role.
Requirements:
•Strong Python development experience in production applications.
•Experience building APIs and backend services, ideally with FastAPI.
•Proven experience building applications with LLMs, using LangChain and/or LangGraph and agentic workflows.
•Experience developing RAG solutions and integrating multiple systems and data sources via REST APIs.
•Solid engineering practices — automated testing, source control, code review and CI/CD — with a focus on production-quality software over prototypes.
•A good understanding of production generative AI challenges: retrieval quality, grounding, context management, evaluation, reliability and performance.
Nice to have:
Experience in any of the following would be particularly valuable: complex RAG architectures (multi-stage retrieval, hybrid search, reranking, agent-driven retrieval); graph databases and GraphRAG, particularly ArangoDB; Azure AI services (Azure OpenAI, AI Search, Cosmos DB, AKS, Functions); vector/semantic search; Docker and Kubernetes; multi-tenant applications; LLM evaluation and observability; and Angular, NgRx or .NET / C# development.
Benefits:
•25 days of annual leave plus an extra WTW day to relax and recharge.
•Comprehensive health and wellbeing offering including private healthcare, life insurance, group income protection, and regular health assessments.
•Defined contribution pension scheme, featuring matched contributions up to 10% from the company.
•Hybrid working options, access to an employee assistance programme, and a fully paid volunteer day.
•Optional additional perks including an electric vehicle car scheme, share scheme, cycle-to-work programme, dental and optical cover, critical illness protection, and much more.
