Knowledge & Data Platform Lead

Capgemini; Greater London; Híbrido; GBP 90 000 - 140 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Hybrid work model

Training opportunities

Wellbeing initiatives

Inclusive recruitment

Resumo da oferta

Capgemini London seeks a Knowledge & Data Platform Lead to build and maintain a production-grade knowledge graph supporting an AI-native product organization. You will implement ontology, schema, and entity resolution, and ensure secure access controls for regulated data.

You will oversee the retrieval stack, data pipelines, and governance across product lines, enabling robust AI agents with compliant memory management and performance evaluation.

Qualificações

• Production data engineering with Python and SQL.
• Knowledge of graph engineering, ontology modeling, and Neo4j.
• Entity resolution across disparate systems.
• Experience with AI retrieval systems, embeddings and vector stores.
• Handling regulated data including PII and PHI.
• Experience with AI coding assistants in daily workflow.
• Experience in financial crime, fraud detection, or payments graph work is a plus.
• Ability to evaluate retrieval performance and analytical data platform knowledge.

Responsabilidades

• Develop and maintain the knowledge graph in production, including implementing the ontology, schema, and entity resolution.
• Create and optimize graph retrieval capabilities, focusing on traversal patterns and graph-augmented retrieval for AI agents.
• Oversee the end-to-end retrieval stack, including chunking, embedding strategies, hybrid search, and performance evaluation.
• Manage data pipelines from client systems, ensuring proper ingestion, mapping, quality checks, and monitoring.
• Maintain an immutable audit trail of system interactions and decisions, along with client-reporting surfaces.
• Implement permission-aware access controls to ensure secure data retrieval based on user identity.
• Govern data for agent memory, including episodic and precedent memory management.
• Establish data contracts between line pipelines and the shared retrieval plane to ensure consistent entity modeling across product lines.

Conhecimentos

Python

SQL

Pipeline Orchestration

Graph Engineering

Entity Resolution

Embeddings

Hybrid Search

PII/PHI Handling

AI Coding Assistants

Financial Crime

Ferramentas

Neo4j

Vector Stores

Embedding Techniques

Descrição da oferta de emprego

Knowledge & Data Platform Lead Overview

Company Name Capgemini

Job Role Knowledge & Data Platform Lead

Qualifications Not Specified

Category IT Jobs

Job Type Full Time

Location London

In this role, you will be instrumental in developing and maintaining the knowledge graph that supports our AI-native product organization within Capgemini Financial Services. Your work will involve creating systems that transform sensitive and regulated knowledge into accessible formats for AI agents, ensuring that the information is both secure and usable.

Key Responsibilities

• Develop and maintain the knowledge graph in production, including implementing the ontology, schema, and entity resolution.
• Create and optimize graph retrieval capabilities, focusing on traversal patterns and graph-augmented retrieval for AI agents.
• Oversee the end-to-end retrieval stack, including chunking, embedding strategies, hybrid search, and performance evaluation.
• Manage data pipelines from client systems, ensuring proper ingestion, mapping, quality checks, and monitoring.
• Maintain an immutable audit trail of system interactions and decisions, along with client-reporting surfaces.
• Implement permission-aware access controls to ensure secure data retrieval based on user identity.
• Govern data for agent memory, including episodic and precedent memory management.
• Establish data contracts between line pipelines and the shared retrieval plane to ensure consistent entity modeling across product lines.

Requirements

• Proven experience in production data engineering, particularly with Python, SQL, and pipeline orchestration frameworks.
• Deep understanding of graph engineering, including schema and ontology modeling, and experience with production graph databases like Neo4j.
• Expertise in entity resolution, capable of matching data across disparate systems.
• Familiarity with retrieval systems for AI workloads, including embeddings, vector stores, and hybrid search techniques.
• Knowledge of regulated data handling practices, including PII and PHI management.
• Hands-on experience with AI coding assistants in a daily workflow.
• Experience in graph work related to financial crime, fraud detection, or payment systems is a plus.
• Ability to demonstrate retrieval evaluation experience and analytical data platform knowledge.

Benefits

• Flexible working arrangements with a hybrid model that includes office, client site, and home working.
• Access to a wide range of training and development opportunities, including certifications from recognized institutions.
• Participation in a Peer Recognition Portal to acknowledge and reward employee contributions.
• Support for employee wellbeing through mental health initiatives and access to wellbeing apps.
• A commitment to inclusive recruitment practices as a Disability Confident Employer.

Degree Requirement: Not Specified

Visa Sponsorship May be