Principal AI/RAG Engineer

Our client is a leading global investment management company headquartered in London, managing over $228 billion in assets for institutional investors worldwide. The project focuses on building foundations for safe and scalable AI adoption in highly regulated financial environments, creating AI-ready data platforms for enterprise data management. This work intersects Data Engineering, AI, Retrieval-Augmented Generation (RAG) systems, and enterprise-scale information management.

Must Have:

• 6+ years of commercial Python development experience.
• 2+ years hands-on experience building production LLM and RAG systems.
• Strong understanding of retrieval pipelines, vector databases, structured information extraction, and AI operational tooling.
• Experience with evaluation frameworks such as Langfuse, RAGAS, DeepEval or similar.
• Expertise in hybrid retrieval techniques: keyword search, semantic search, cross-encoder reranking, retrieval optimization.
• Experience with document processing and extraction pipelines.
• Knowledge of OCR-based document processing.
• Practical experience working with AI agents and agentic workflows.
• Advanced PostgreSQL knowledge including relational data modeling, JSONB, schema migrations, data transformations.
• Strong understanding of data governance, provenance, and traceability.
• Excellent communication skills in English.

Nice to Have:

• SharePoint and Microsoft Graph API integrations.
• Knowledge graph technologies such as Neo4j or Apache AGE.
• Experience building permission-aware retrieval systems.
• Experience with MCP tools, AI agents or AI coding assistants.
• Legal, contract management or document intelligence domain knowledge.
• Financial services experience.
• Experience working in regulated enterprise environments.
• Bitemporal data modeling and document lineage solutions.
• Cost and token-efficiency optimization for LLM applications.

• Design and develop production-grade AI and RAG solutions.
• Build and maintain evaluation frameworks, automated test suites, and quality gates for AI systems.
• Enhance retrieval pipelines using hybrid search, reranking, and metadata-driven filtering.
• Develop document intelligence solutions including structure-aware parsing, chunking, and information extraction.
• Build metadata and entity extraction pipelines with confidence scoring and human review workflows.
• Design synchronization mechanisms for enterprise content platforms.
• Develop document lineage, temporal views, and document relationship models.
• Contribute to knowledge graph and query orchestration capabilities.
• Create monitoring, observability, and quality dashboards for AI services.
• Ensure provenance, traceability, and governance across generated answers and extracted information.
• Collaborate directly with client stakeholders in a regulated financial environment.

Przesyłając ten formularz, wyrażasz zgodę na przetwarzanie Twoich danych osobowych zgodnie z naszą Polityką Prywatności Rekrutacji - https://career.intellias.com/recruitment-privacy-notice. Jeśli chcesz wycofać swoją zgodę lub masz jakiekolwiek pytania dotyczące naszej Polityki Prywatności Rekrutacji, skontaktuj się z nami([email protected])