Job Description

Job Title: Knowledge & Data Platform Lead

About us

NewCo is a new AI-native product organisation within Capgemini Financial Services. We build products, not projects: software for insurance claims, payment operations, and health operations, sold to banks, insurers, and health plans. Three product lines run on one shared platform, built by a deliberately small, senior team. Our engineering model is agentic: engineers author the specifications, tooling, evaluation suites, and guardrails, and AI agents do most of the implementation. Humans own every consequential decision, and in our regulated domains some decisions are human-only by design.

About the job you’re considering

Hybrid working: The places that you work from day to day will vary according to your role, your needs, and those of the business; it will be a blend of Company offices, client sites, and your home; noting that you will be unable to work at home 100% of the time.

If you are successfully offered this position, you will go through a series of pre-employment checks, including: identity, nationality (single or dual) or immigration status, employment history going back 3 continuous years, and unspent criminal record check (known as Disclosure and Barring Service)

The role

Our agents are only as good as the knowledge and context they run on, and in claims, payments, and health that knowledge is regulated, sensitive, and scattered across client estates. You will own the knowledge layer all three product lines build on: the enterprise knowledge graph that makes domain intelligence queryable (fraud networks and payment chains are graph problems from the first client), the governed retrieval plane that grounds every agent answer, the context engineering discipline that decides what enters a model's context window and at what cost, and the knowledge lifecycle that keeps what agents know current, versioned, and auditable. This is a platform leadership role with a governance mandate, not a governance role at platform distance.

What you will own

• The enterprise knowledge graph: ontology and schema design, the pipelines that build and refresh it from production data, and graph retrieval as a first-class platform capability for the product lines
• RAG optimisation end to end: chunking and embedding strategy, hybrid and graph-augmented retrieval, reranking, and the evaluation harness that measures grounding, relevance, and freshness and gates regressions in CI
• Context engineering as a platform discipline: what enters each agent's context window (retrieved knowledge, agent memory, precedents, tool results), in what order and at what token budget, as shared patterns the product lines adopt instead of bespoke prompt plumbing
• Knowledge management for AI systems: the lifecycle from source documents to governed, versioned knowledge agents may use; curation, provenance, freshness, and deprecation, per tenant and per caller
• The agent memory plane: how episodic and precedent memory is written, recalled, and governed across the product lines
• Permission-aware retrieval where the caller's identity travels with every query, document-level access controls, multi-tenant isolation, and the immutable audit trail of what our systems read, decided, and did
• The data flywheel for model adaptation: production data, curated and governed, becomes the training and evaluation datasets behind the LLMs and SLMs we tune ourselves

What you will need

• Graph engineering depth: you have designed ontologies and graph schemas and operated production graph systems (Neo4j or comparable), including graph retrieval for AI workloads
• RAG in production: you have built and optimised retrieval pipelines (embedding strategy, hybrid search, reranking, retrieval evaluation) and can show the quality curves you moved
• Context engineering fluency: you treat the context window as an engineered, budgeted artifact and have built context assembly, compaction, or agent memory systems
• Knowledge management for AI: curation, provenance, and versioning of enterprise knowledge for machine consumption, not just human search
• Regulated-data credentials: you have operated under financial-services data regulation (ideal) or GDPR and can design for auditability from day one
• The technical leadership to set standards other senior engineers follow without a reporting line
• Daily, hands-on use of AI tools in your own work

What sets you apart

• Insurance or payments data domain knowledge
• Model-risk governance exposure (SR 11-7 or equivalent), prompt/retrieval governance, or AI-governance frameworks
• Graph data science in production: entity resolution, community detection, or link prediction applied to problems like fraud networks or payment chains
• You track retrieval and memory research (graph retrieval, agent memory architectures) and have shipped systems informed by it

The reference stack

The reference technology stack for this role is our supported paved road: self-hosted LangSmith and LangGraph Platform as the agent runtime and evaluation plane, model providers behind a swappable gateway seam, PostgreSQL with pgvector plus ClickHouse and S3-compatible object storage as the data platform, Neo4j Enterprise as the semantic knowledge graph, an agent memory plane serving episodic and precedent memory over MCP, MCP-native connectors, OpenTelemetry and Grafana for observability, all on CNCF-conformant Kubernetes with Helm and Argo CD, deployable to any hyperscaler or on-prem. A tool-for-tool match is not expected: analogous experience counts fully. If you have built and operated systems of this shape on comparable components (a different orchestration framework, graph engine, evaluation platform, or serving stack), you have what we are looking for.

How we work

• Engineers write specs, harnesses, evals, and guardrails; AI agents execute the implementation loops. Review, not typing, is where engineering judgment goes.
• Three human gates govern everything we ship: spec approval, merge, and release. Regulated code paths (money movement, authentication, cryptography, secrets) are always human-owned.
• Small and senior by design. No separate QA function, no scrum masters; quality comes from evaluation gates and whole-team review rituals.
• Domain experts (claims practitioners, payment scheme experts, clinicians) are full-time members of the product teams you will serve.

Success in year one

• The knowledge graph serves two product lines in production, built and refreshed by pipelines rather than curation heroics, with graph retrieval answering agent queries
• Retrieval is permission-aware and tenant-isolated in production, and the grounding and relevance metrics that gate merges visibly moved on optimisations you shipped
• Context assembly is a paved path: product-line agents compose retrieval, memory, and precedents through shared platform patterns, with token budgets that hold
• A client's compliance team completes a provenance review (what an agent read, and why it was allowed to) without a bespoke evidence hunt

We are a Disability Confident Employer

Capgemini is proud to be a Disability Confident Employer (Level 2) under the UK Government’s Disability Confident scheme.As part of our commitment to inclusive recruitment, we will offer an interview to all candidates who:

• Declare they have a disability, and
• Meet the minimum essential criteria for the role.

Please opt in during the application process.

Make it real – what does it mean for you?

• We realise a Total Reward package should be more than just compensation. At Capgemini we offer range of core and flexible benefits and have a Peer Recognition Portal called Applaud.
• You’d be joining an accredited Great Place to work for Wellbeing in 2024. Employee wellbeing is vitally important to us as an organisation. We see a healthy and happy workforce a critical component for us to achieve our organisational ambitions.
  To help support wellbeing we have trained ‘Mental Health Champions’ across each of our business areas, and we have invested in wellbeing apps such as Thrive and Peppy.
• You will be empowered to explore, innovate, and progress. You will benefit from Capgemini’s ‘learning for life’ mindset, meaning you will have countless training and development opportunities from thinktanks to hackathons, and access to 250,000 courses with numerous external certifications from AWS, Microsoft, Harvard ManageMentor, Cybersecurity qualifications and much more.

Capgemini. Make it real.

Why you should consider Capgemini

Growing clients’ businesses while building a more sustainable, more inclusive future is a tough ask. When you join Capgemini, you’ll join a thriving company and become part of a collective of free-thinkers, entrepreneurs and industry experts. We find new ways technology can help us reimagine what’s possible. It’s why, together, we seek out opportunities that will transform the world’s leading businesses, and it’s how you’ll gain the experiences and connections you need to shape your future. By learning from each other every day, sharing knowledge, and always pushing yourself to do better, you’ll build the skills you want. You’ll use your skills to help our clients leverage technology to innovate and grow their business. So, it might not always be easy, but making the world a better place rarely is.

About Capgemini

Capgemini is an AI-powered global business and technology transformation partner, delivering tangible business value. We imagine the future of organisations and make it real with AI, technology and people. With our strong heritage of nearly 60 years, we are a responsible and diverse group of 420,000 team members in more than 50 countries. We deliver end-to-end services and solutions with our deep industry expertise and strong partner ecosystem, leveraging our capabilities across strategy, technology, design, engineering and business operations. The Group reported 2024 global revenues of €22.1 billion.

Make it real