Knowledge & Data Platform Lead
Capgemini
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 part of a pioneering AI-native product organization within Capgemini Financial Services, focusing on building innovative software solutions for insurance claims, payment operations, and health operations. The position emphasizes a hybrid working model, where your daily work environment will vary between company offices, client sites, and your home, with the understanding that full-time remote work is not an option.
Key Responsibilities
- Develop and maintain the knowledge graph in production, including implementing the ontology and schema, entity resolution, and managing the pipelines that build and refresh the graph from client estates.
- Establish graph retrieval as a key capability, focusing on traversal patterns, graph-augmented retrieval for agents, and optimizing query performance under real-world conditions.
- Oversee the end-to-end retrieval stack, including chunking and embedding strategies, hybrid search, reranking, and performance measurements to ensure improvements are effective.
- Manage data pipelines from client systems, ensuring proper ingestion, mapping, quality checks, freshness monitoring, and unattended operation with meaningful alerts.
- Maintain an immutable audit trail of system interactions, decisions made, and client reporting surfaces based on this data.
- Implement permission-aware access controls, ensuring that the identity of the caller is tracked with every query and that document-level controls are enforced.
- Develop data for the agent memory plane, focusing on how episodic and precedent memory is written, recalled, expired, and governed.
- Establish data contracts between line pipelines and the shared retrieval plane to prevent duplicate entity modeling across product lines.
Qualifications
- Proven experience in production data engineering, particularly with Python, SQL, and a pipeline orchestration framework, managing systems relied upon by others.
- Deep understanding of graph engineering, including schema and ontology modeling, experience with production graph databases like Neo4j, and proficiency in a graph query language.
- Expertise in entity resolution, capable of matching individuals, organizations, policies, accounts, and claims across disparate systems.
- Experience with retrieval systems tailored for AI workloads, including embeddings, vector stores, hybrid search, and reranking, along with the ability to evaluate these systems effectively.
- Knowledge of regulated data handling, including PII and PHI, data lineage, retention, minimization, and the importance of masking test data.
- Daily hands-on experience using AI coding assistants as part of the workflow.
Benefits
- A comprehensive Total Reward package that includes both core and flexible benefits.
- Access to a Peer Recognition Portal called Applaud.
- Opportunities for continuous learning and development, including access to 250,000 courses and various external certifications.
- Support for employee wellbeing through trained Mental Health Champions and investment in wellbeing apps like Thrive and Peppy.
- A commitment to inclusive recruitment practices as a Disability Confident Employer.
Capgemini is dedicated to fostering a diverse and inclusive workplace, encouraging all qualified candidates to apply.
Degree Requirement: Not Specified
Visa Sponsorship May be
To apply for this job please visit careers.capgemini.com.