AI Data/Graph Engineer

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)

About us

We are developing 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.

The role

Our agents are only as good as the knowledge they run on, and in claims and payments that knowledge is regulated, sensitive, and scattered across client estates. You will build the systems that turn it into something an agent can use safely: the knowledge graph that makes domain intelligence queryable, the retrieval stack that grounds every answer, the pipelines that keep both current, and the access controls that ensure a query only ever returns what its caller is entitled to see. Fraud networks and payment chains are graph problems from the first client, so this is not a document-search role wearing a graph label.

This seat is deliberately written to sit either in the platform group, building the shared knowledge layer both product lines consume, or embedded in one line, owning its system of record and domain data model. We will decide which with you, based on where your strengths land.

What you will own

• The knowledge graph in production: implementing the ontology and schema, entity resolution, and the pipelines that build and refresh the graph from client estates
• Graph retrieval as a first-class capability: traversal patterns, graph-augmented retrieval for agents, and query performance under real load
• The retrieval stack end to end: chunking and embedding strategy, hybrid search, reranking, and the measurements that tell you a change actually helped
• Data pipelines from client systems: ingestion, mapping, quality checks, freshness monitoring, and unattended operation with meaningful alerts
• The immutable audit trail of what our systems read, decided, and did, and the client-reporting surfaces built on it
• Permission-aware access: the caller's identity travels with every query, document-level controls hold, and tenant isolation is provable rather than assumed
• Data for the agent memory plane: how episodic and precedent memory is written, recalled, expired, and governed
• Data contracts between line pipelines and the shared retrieval plane, so two product lines do not model the same entity two ways

What you will need

• Production data engineering: Python, SQL, and a pipeline orchestration framework, running systems that other people depend on
• Graph engineering depth: schema and ontology modelling, a production graph database (Neo4j or comparable), and fluency in a graph query language
• Entity resolution at real-world quality: matching people, organisations, policies, accounts, and claims across systems that disagree with each other
• Retrieval systems for AI workloads: embeddings, vector stores, hybrid search, reranking, and how to evaluate any of it honestly
• Regulated data discipline: PII and PHI handling, lineage, retention, minimisation, and why masking test data is not optional
• Daily, hands-on use of AI coding assistants as part of your own workflow

What sets you apart

• Graph work on financial crime, fraud rings, AML networks, or payment chains
• Fluency with a domain data model we integrate against: ISO 20022, Guidewire, or a core banking or policy administration schema
• Retrieval evaluation experience: you can show the quality curves you moved and explain what caused each step
• Analytical data platform depth (ClickHouse or comparable) alongside the transactional and graph stores
• Context engineering: treating the model's context window as a budgeted, engineered artifact rather than a prompt

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 scrum masters and no separate delivery-management layer; quality is owned inside the product team, by the engineers who build and the quality and evaluation engineers who work alongside them.
• Domain experts (claims practitioners and payment scheme experts) are full-time members of the teams you serve.

Success in year one

• Graph build and refresh run unattended against a live client estate, with freshness measured and alerted rather than assumed
• Retrieval quality for at least one product line has improved on a measure the evaluation engineers accept, and you can explain what moved it
• Permission-aware retrieval holds under adversarial testing, and multi-tenant isolation has been demonstrated to a client's security function
• A second product line reuses your data model and contracts instead of building its own

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