Data Scientist - Credit Risk Modelling

Data Scientist - Credit Risk Modelling

Hybrid in London or remote in the UK

We’re looking for a Data Scientist to join our Credit Risk Modelling team.

You'll work on the credit models that sit at the core of iwoca's lending business – the models that decide who we lend to, on what terms, and how far the product can grow.

The company

We’ve already cleared the way for 100,000 businesses with more than £4 billion in funding. Our passionate team is driven to help even more SMEs succeed, through access to better finance and other services that make running a business easier. Our ultimate mission is to support one million SMEs in their defining moments, creating lasting impact for the communities and economies they drive.

The team

The Credit Risk Modelling team owns credit risk and customer lifetime value (CLtV) modelling for iwoca's UK and German lending. That covers the probabilistic machine learning models behind every credit decision, plus the CLtV models that shape pricing and portfolio strategy.

The team is around twelve data scientists, who combined create models to efficiently drive fully automated and human-in-the-loop decision making. This forms the core analytical team that interface with and support smaller analytic functions in other parts of the business.

The role

As a Data Scientist in Credit Risk Modelling, you'll use iwoca's lending data to answer credit risk and CLtV questions, and build what you find into the team's production models. The work ranges from keeping today's models accurate as conditions change, through incremental improvements, to research that could replace them.

You'll help choose the team's projects and put forward your own. With AI, prototyping is cheap enough for you to test ideas that once wouldn't have made the priority list. The R&D share of the role is growing as a result. You'll learn credit modelling in depth from several senior data scientists.

Live examples of the work:

• Causal estimation of offer terms. Estimating the causal effect of amount, duration, and price on customer outcomes.
• Unifying automated and manual models. Finding a principled way to put the two model families, which optimise slightly different objectives, on a common cost function.
• IFRS accounting model. Developing a multi-stage model where recovery predictions feed back to improve the upfront loss estimates that International Financial Reporting Standards (IFRS) require.
• Generalising credit and CLtV. Exploring whether a single, more general model could replace the separate credit and CLtV models.

The requirements

Essential:

• Applied statistics. You have a background in statistics from a quantitative field – typically a degree or Master's in Statistics, Mathematics, Physics, or similar. You've applied it to real-world data, in research or at work. You know when the data breaks a method's assumptions, and what that does to your answer.
• Probabilistic reasoning. You quantify the uncertainty in each estimate, and treat calibration as a first-order concern.
• Research mindset. You've tested new modelling ideas of your own, and judged which were worth taking further.
• Judgement. You critically evaluate model output – yours, a colleague's, or an LLM's – and can explain why a choice is right. You defend your reasoning under challenge, and challenge others' when the evidence points elsewhere.
• Analytical ownership. You've taken ambiguous problems from framing the question to a decision the business acted on. You give an early answer and update it as new evidence comes in.
• AI leverage. You've used AI to produce work you couldn't have delivered without it – a prototype, an automation, or a modelling pipeline others use. You judge where it helps and where it doesn't.
• Communication. You write and speak clearly, directly, and concisely. You adapt technical detail to your audience.

Bonus:

• Domain experience. You've worked in credit risk, lending, or customer lifetime value modelling.
• Production ML. You've built supervised ML models end to end – exploration, training, deployment, and monitoring.
• Non-linear methods. You can think in terms of the cost function and inductive biases of your models.
• Bayesian methods. You've used hierarchical models, MCMC, or Bayesian updating in real work.
• Time series modelling. You've modelled temporal data where autocorrelation, drift, or seasonality mattered.
• Coding. You can write code for analysis. The team works in Python

The salary

We expect to pay from £60,000 – £90,000 for this role. But, we’re open-minded, so definitely include your salary goals with your application. We routinely benchmark salaries against market rates, and run quarterly performance and salary reviews.

The benefits

• Flexible working hours.
• Medical insurance from Vitality, including discounted gym membership.
• A private GP service (separate from Vitality) for you, your partner, and your dependents.
• 25 days’ holiday per year, an extra day off for your birthday, the option to buy or sell an additional five days of annual leave, and unlimited unpaid leave.
• A one-month, fully paid sabbatical after four years.
• Instant access to external counselling and therapy sessions for team members that need emotional or mental health support.
• 3% Pension contributions on total earnings.
• An employee equity incentive scheme.
• Generous parental leave and a nursery tax benefit scheme to help you save money.
• Electric car scheme and cycle to work scheme.
• Two company retreats a year: we’ve been to France, Italy, Spain, and further afield.