Senior Python / AI Data Engineer

Our client is a leading global investment management company headquartered in London, managing $228+ billion in assets for institutional investors, pension funds, wealth managers, and other sophisticated clients worldwide.

The company specializes in quantitative investing, alternative investments, systematic trading strategies, and technology-driven asset management, with data science, machine learning, and AI playing a central role in its investment and research processes.

About the Project

The project focuses on building the foundational capabilities required for safe and scalable enterprise AI adoption, specifically Agentic Security and AI-Ready Data Foundations.

The team is building data platforms that enable AI agents to securely discover, understand, retrieve, and reason over trusted enterprise data. The role will focus on building catalogue, semantic, entitlement, retrieval, and analytical layers across large on-premise data estates in a highly regulated financial environment.

The Role

We are looking for a Senior Python / AI Data Engineer with strong production Python and data-engineering experience and hands-on expertise in LLM and RAG systems.

Responsibilities

• Build and optimize production-grade RAG and retrieval pipelines.
• Develop hybrid search combining keyword and semantic retrieval, result merging, and reranking.
• Build automated LLM/RAG evaluation frameworks, benchmarks, and release gates.
• Develop structure-aware document processing pipelines, including OCR and multilingual content.
• Build scalable LLM-based extraction pipelines with schemas, confidence scoring, and human review.
• Design and maintain PostgreSQL models, JSONB structures, migrations, and derived views.
• Implement document provenance, citations, lineage, supersession, and temporal views.
• Build synchronization pipelines for enterprise content platforms.
• Contribute to controlled knowledge graphs and AI query orchestration.
• Implement permission-aware retrieval and data-access controls.
• Expose capabilities to AI assistants through MCP tools or agent skills.
• Build monitoring, quality dashboards, freshness controls, and corpus health checks.
• Work closely with client and engineering teams in a regulated financial-services environment.

Requirements

• 5+ years of production Python development.
• 2+ years of production LLM/RAG engineering.
• Strong experience with retrieval pipelines, vector stores, structured extraction, and LLM operational tooling.
• Experience building RAG evaluation frameworks using Langfuse, RAGAS, DeepEval, or similar tools.
• Strong understanding of hybrid retrieval, embeddings, reranking, and retrieval optimization.
• Experience with structure-aware document parsing, chunking, OCR, and multilingual documents.
• Strong PostgreSQL skills, including relational modelling, JSONB, migrations, and data transformations.
• Experience with data provenance, citations, lineage, and trustworthy AI outputs.
• Strong understanding of AI agents and agentic architectures.
• Fluent spoken and written English.
• Bachelor’s degree in Computer Science, Engineering, Data Science, or a related field.

Nice to Have

• SharePoint and Microsoft Graph API experience.
• Bitemporal data modelling and document lineage.
• Knowledge of Neo4j, Apache AGE, or similar graph technologies.
• Permission-aware retrieval and enterprise authorization.
• LLM token and cost optimization.
• MCP tools/skills and AI coding-agent experience.
• Experience with regulated or on-premise enterprise environments.

Why Join?

This is an opportunity to work at the intersection of AI, data engineering, and financial services, solving complex problems around trusted enterprise data and agentic AI.

The role offers significant technical ownership and the opportunity to build foundational capabilities across RAG, AI agents, data governance, knowledge graphs, provenance, security, and AI-ready data platforms within a global investment-management organization.