Principle Data Scientist

Who We Are

Provenir is the unified Decision Intelligence Platform that gives enterprises full control over end- to-end customer decisioning — to manage risk, drive growth, and transform business outcomes. By consolidating data, AI models, intelligence, agents and governance into a single decisioning environment, Provenir empowers business teams to configure and evolve strategy directly, while maintaining enterprise-grade reliability and regulatory compliance. Trusted by 120+ institutions in 60+ countries, Provenir processes over 4 billion decisions annually — turning architectural coherence into sustained risk performance and measurable value. Ready to solve meaningful challenges, work with enterprise customers, and help shape the future of AI-powered decisioning? Join us.

📍 Remote first – UK/Europe

🛠️ Python, SQL, graph analytics, identity/entity resolution, AWS

🚀 Own the strategy and build of our identity graph and graph-driven identity intelligence

🕛 Senior individual contributor – deep graph expertise, hands-on, with the ambition to grow a team

💰 Competitive compensation

💚 Fantastic benefits including Health Plans, WFH allowance and Macbook Pro

We are Provenir AI, part of the Provenir group — a global fintech building the decisioning and analytics products that financial services and other industries rely on to make smarter, faster decisions.

You'll own the strategy, design, and evolution of our identity graph and the intelligence we build on top of it powering identity resolution, identity intelligence, and next-generation fraud solutions across our core products, including our 1datapipe® platform and Living Identity® data.

This is a senior individual contributor role that pairs deep graph and entity-resolution expertise with genuine product thinking. You'll be hands-on from day one, shaping how the graph is built, queried, and enriched and how it becomes real product capability. As you prove the value, you'll grow a data science team around you over time.

You'll thrive here if you like autonomy, don't need a fully formed data science org around you, and are motivated by shipping intelligence that improves the product working embedded with engineering and product teams.

• The core identity graph model and its long-term evolution

• Feature discovery from entity relationships and connected data

• Product capabilities built on the graph, and the analytical workflows behind them

• Standards for how identity intelligence is built, validated, explained, and reused

• Technical direction on the analytical methods, graph libraries, and tooling we build with partnering with engineering on the underlying data architecture

• Cross-functional alignment between product goals and our data capabilities

• Data science standards, tools, and methodology across Provenir AI — how we experiment, validate, and ship

• Pragmatic use of LLMs and agentic tooling to add value, whether internally for productivity or directly in the product

• Design and evolve a deterministic identity graph that represents key entities, relationships, and business logic

• Identify and prioritise the features, signals, and patterns in our connected data that create product value

• Build and guide analytics pipelines for link analysis, identity resolution, clustering, ranking, anomaly detection, and discovery

• Partner with data engineers to define ingestion, enrichment, validation, and publishing workflows into the identity data

• Work with product managers and stakeholders to translate ambiguous business problems into product features

• Prototype and evaluate approaches for identity resolution, identity intelligence, fraud detection, and risk intelligence

• Partner with data engineers to define the quality and coverage signals that matter for trustworthy identity intelligence — coverage, match confidence, and accuracy

• Select the right technologies and patterns, and create clear documentation and decision frameworks so the work can be reused across teams

• Mentor engineers and data scientists on graph methods, modelling, and analytical techniques and grow a team as value is proven

• Strong experience in graph data science, knowledge graphs, or graph/network analytics

• Hands-on experience building and working with graph structures using libraries or databases (e.g. Neo4j, Amazon Neptune, JanusGraph, GraphFrames, NetworkX, or similar)

• Experience with identity resolution, entity resolution, or link analysis

• Strong Python and SQL skills

• A genuine product mindset, you start from the business problem and the product outcome, not the technique, and you can prioritise accordingly

• Ability to design analytical approaches from ambiguous problems

• Track record of operating in production environments with quality, scale, and reliability requirements

• Strong communication skills and comfort working embedded with product and engineering teams

• Although not essential, it would be great if you have experience with:

• Building graph-enabled products in identity, fraud, financial crime, risk, or AI-driven decisioning

• Graph embeddings or other graph-native ML methods

• Ontology design, semantic modelling, or taxonomy development

• Large-scale distributed data processing (e.g. Spark, Dask)

• Building and growing data science teams

• Working in scale-up or early-stage environments

This is a genuinely hands-on role. You'll be writing code and building graph pipelines yourself, not just directing and that's expected to remain true for the foreseeable future. The "grow a team" part comes after you've proven the value and established the foundations.

You'll be the most senior data scientist in the Provenir AI team, which means real independence and impact, but also means you won't have a large peer group of data scientists around you initially. If you thrive when given ownership and like building things from scratch, this could be ideal.

Much of the work is about making relationship data better, more connected, and more usable not just building models for their own sake. Credibility comes from shipping production capabilities that improve the product, working very closely with software and data engineers.

The identity graph and Living Identity® data are the priority and where you'll make your mark first. Over time, as the most senior data scientist, you'll also shape how data science is done across Provenir AI the tools, methods, and pragmatic use of LLMs and agents that add value, whether internally or in the product.

The interview process would typically be structured as follows:

Team Fit. A conversation with our CTO to explore how you work, what you're looking for, and how you'd fit with the team

Case Study. We'll share a realistic identity/graph data problem for you to work through ahead of the next round

Technical Interview. With data science and/or engineering leadership — you'll present and discuss your case study, and we'll explore your approach to graph and identity problems, production systems, and team building

Final Interview. A conversation with our CEO on vision, impact, and how you'd approach the first 90 days

• Comprehensive private health cover and wellness plans

• Flexible and remote-friendly opportunities

• Maternity/paternity leave

• Retirement benefits such as pension contributions to plan for your future

• Macbook Pro

Our employees are our top priority; we offer comprehensive health and wellness plans. You will enjoy paid time off and company holidays, flexible and remote-friendly opportunities, and maternity/paternity leave.

At Provenir, we recognize that diversity and inclusion make our teams stronger. We are committed to equal employment opportunity and welcome everyone regardless of race, colour, ancestry, religion, national origin, age, sex, gender identity, sexual orientation, disability, marital status, domestic partner status, citizenship, or veteran status or medical condition. We encourage people from all backgrounds to apply.