AI Engineer - RAG & Document Intelligence

Lumen Dynamics is a technology company of over 500 experts, empowering large organizations to solve complex business challenges with modern IT solutions - from sales systems and automation to data platforms and AI. We operate where technology must be reliable, secure, and scalable. We deliver end-to-end projects: from analysis and architecture through implementation to development and maintenance. We are a trusted partner of industry leaders such as Salesforce, Veeva, UiPath, and Databricks. Model: remote Employment type: full-time Role summary You'll be at the heart of one of the most impactful AI initiatives at an international Consumer Health company. Your mission: build a platform from scratch that lets business users retrieve, synthesize, and act on knowledge locked inside complex enterprise documents — using plain language. This is a greenfield role blending engineering and research, where you design and implement a context-aware, multi-agent AI system that will fundamentally change how the entire organisation interacts with its knowledge assets. Responsibilities Design and build multi-agent AI systems — architect and implement agentic components in Python (routers, planners, verifiers, supervisors) with a focus on composability and adaptability as LLM capabilities evolve. Build robust document parsing pipelines — handle PDFs, Word documents, presentations, scanned files, and mixed-format corpora; extract structured meaning from noisy inputs including tables, charts, and figures. Architect end-to-end RAG pipelines — own the full stack from document ingestion and semantic chunking, through embedding, indexing, hybrid search, and re-ranking, to dynamic context assembly within token limits. Instrument, evaluate, and continuously improve AI quality — build automated regression testing frameworks, support A/B testing of LLM configurations, and integrate human feedback loops. Contribute to the AI engineering platform — build reusable frameworks and components, manage production-grade code in GitHub, conduct peer reviews, and contribute to architectural and technology stack decisions. Requirements Must-have: Strong Python engineering with production-grade Generative AI system experience Hands-on experience with multi-agent AI frameworks: LangGraph , LangChain , or Pydantic AI Deep experience building RAG pipelines: chunking strategies, embedding models, hybrid search, re-ranking ( LightRAG , LlamaIndex , LangChain ) Solid experience with document parsing and multimodal document understanding (tables, charts, figures) Strong API development skills ( FastAPI ) Proficiency with Azure cloud services ( Azure Apps , Containers , Storage , AI Search , AI Foundry ) and/or AWS equivalents Experience with Databricks : Delta Lake , Unity Catalog , MLflow Familiarity with AI observability and evaluation frameworks: RAGAS , DeepEval , Langfuse Experience with vector databases ( pgvector , Pinecone , Qdrant , Weaviate ) and Docker containerisation Fluent English, both written and spoken Nice-to-have: Hands-on experience with Databricks GenAI products: Vector Search , Agent Framework , Knowledge Assistance , Genie , Agent Bricks Experience with LLM context management and prompt engineering Knowledge of Model Context Protocol (MCP) for tool integration Understanding of CI/CD principles, GitHub Actions , and Infrastructure as Code ( Terraform , ARM Templates ) Understanding of knowledge management, taxonomy design, and metadata enrichment for enterprise document repositories Why this role is different Greenfield from day one — you're building a foundational AI capability from scratch, not maintaining legacy systems or following pre-defined specs. Real research component — you'll be answering open architectural questions that genuinely matter; this is applied research, not ticket execution. Organisation-wide reach — the platforms you build will serve commercial, marketing, product supply, and R&D teams across a global organisation. Cutting-edge stack — multi-agent orchestration, compound AI systems, and LLM-powered document intelligence at enterprise scale. Employment conditions: B2B contract, Daily support from team leaders, Dedicated certification budget, Assistance in defining and support in your development path, Benefits package, Integration trips/events.