Senior/Lead Data Scientist (Credit Risk)

About The Company

About Cleo

At Cleo, we're not just building another fintech app. We're embarking on a mission to fundamentally change humanity's relationship with money. Imagine a world where everyone, regardless of background or income, has access to a hyper-intelligent financial advisor in their pocket. That's the future we're creating.

Cleo is a rare success story: a profitable, fast-growing unicorn with over $300 million in ARR and growing over 2x year-over-year. This isn't just a job; it's a chance to join a team of brilliant, driven individuals who are passionate about making a real difference. We have an exceptionally high bar for talent, seeking individuals who are not only at the top of their field but also embody our culture of collaboration and positive impact.

If you’re driven by complex challenges that push your expertise, the chance to shape something truly transformative, and the potential to share in Cleo’s success as we scale, while growing alongside a company that’s scaling fast, this might be your perfect fit.

Follow us on LinkedIn to keep up to date with new product features and insights from the team.

The role

We’re looking for a Lead/Senior Data Scientist to help us measure, monitor, and improve the performance of Cleo’s credit products. This is a level 3 or 4 Analytics role.

This is a hands‑on data science and analytics role. You’ll be analysing behaviour across millions of US users, using rich transactional and behavioural that powers Cleo’s AI money coach and credit products. You’ll spend the majority of your time in SQL and Python, working directly from Cleo’s data warehouse to understand, explain, and improve credit performance.

This is not a traditional underwriting or policy role. You’ll be the analytics owner for [EWA / specific product], with direct line of sight to losses, revenue, and product roadmap. You’ll work closely with other analysts, Risk Modellers, Product Managers, and Engineers to diagnose portfolio trends, build monitoring frameworks, and deliver insights that inform how Cleo manages and optimises risk.

You’ll sit within the Risk & Payments pillar, working at the intersection of data, decisioning, and product, helping us build scalable systems that balance user access with sustainable economics.

You’ll be part of a growing team responsible for driving profitable growth while protecting the business from loss, using data to understand repayment behaviour, model performance, and system-level trade-offs. This is an opportunity to shape how we quantify and manage risk as we expand across new credit products and geographies.

What You’ll Be Doing

• Credit & Risk Performance Analytics

• Write complex SQL/python to pull cohort‑ and event‑level datasets from our warehouse and turn them into clear, decision‑ready analyses.

• Quantify the commercial impact of performance changes (losses, yield, approval rate)

• Design and analyse multivariate experiments on underwriting, pricing, or repayment flows, and translate results into actionable risk strategies

• Analyse arrears, default, and yield trends across Cleo’s credit products.

• Identify emerging risks and shifts in eligibility or repayment behaviour using cohort and segmentation analysis.

• Build and maintain dashboards for portfolio health and performance tracking.

• Design early-warning alerts for anomalies in arrears or model-driven decisioning.

• Model Understanding & Monitoring

• Partner with the Risk Modelling team to turn model health metrics (AUC, PSI, calibration, feature drift) into clear recommendations for policy or product changes.

• Monitor model stability and support investigations into concept drift and feature degradation.

• Quantify the impact of model changes and assess whether observed shifts are model- or market-driven.

• Deep-Dive Investigations

• Conduct root-cause analysis on performance deteriorations (e.g., arrears spikes, yield compression).

• Own investigations from question → analysis → recommendation, and present your work to Risk, Product, and Leadership.

• Use decomposition, SHAP analysis, and driver frameworks to explain variance in loss and yield.

• Support the design and measurement of A/B tests or pilot changes in credit decisioning or repayment operations.

• Forecasting & Scenario Support

• Partner with Finance and Commercial teams to support variance analysis and monthly forecast inputs.

• Model how shifts in repayment or eligibility rates flow through to portfolio loss and profitability.

• Tooling, Frameworks & Collaboration

• Work with Analytics Engineering to improve risk data pipelines and metric definitions.

• Build reusable analysis templates and frameworks for