Senior Data Scientist

Zilch; Greater London; Hybrid; GBP 90,000 - 120,000; Full time

Job summary

Zilch is seeking a Senior Data Scientist to join the Risk team. You will build and optimize production-grade models for credit risk, collections and fraud, using diverse data sources to improve risk outcomes and customer experience.

You will own end-to-end ML pipelines, deploy and monitor models, and partner with product, risk, engineering and analytics teams to drive data-driven decisioning and business growth.

Qualifications

• 3+ years hands-on data science experience in risk, fintech, or related field.
• Strong SQL and Python skills with experience in data analysis and modeling.
• Production deployment, monitoring and iteration of ML models in cloud environments.

Responsibilities

• Develop and optimize models for credit risk, collections and fraud.
• Build robust ML pipelines and model deployment workflows.
• Collaborate with product, risk, engineering and analytics teams.
• Present findings to senior stakeholders with clear storytelling.
• Apply ML methods to improve risk decisioning and business outcomes.

Skills

SQL

Python

NumPy

Pandas

Scikit-Learn

ML Deployment

CI/CD

Git

Looker

DBT

Tools

Amazon SageMaker

Looker

DBT

GitHub Actions

Job description

We're one of Europe's fastest-growing fintech companies – on a mission to create the world's most empowering way to pay.

We launched the product in 2020 and achieved double unicorn status, valued at $2 billion, and since then have taken on more than 6 million customers.

Our mission is to become the best way to pay for anything, anywhere and say goodbye to credit costs for everyone. This is huge. Want to join us?

About the Role.

We are seeking a talented and experienced Senior Data Scientist to join Zilch’s Risk team, with a focus on developing and optimising advanced models in the Risk space, primarily across credit risk, with additional focus on collections optimisation and fraud detection. You will leverage diverse data sources to support key areas across the business, building production-grade models and decisioning solutions that improve risk outcomes, customer experience, and operational efficiency. This role will involve close collaboration with cross-functional teams, including product managers, engineers, risk strategy, credit, collections, fraud, and other data scientists, to ensure data-driven insights are successfully integrated into product strategies, risk decisioning, and business growth initiatives.

This is a hands‑on role for someone who combines strong applied machine learning with modern ML Ops practices. We are looking for a data scientist who can take models from exploration through to production, monitoring, and iteration.

Key Responsibilities.

Work with large and complex datasets to solve a wide array of challenging problems using various analytical and statistical approaches.

Apply technical expertise with quantitative analysis, experimentation, data mining, and the presentation of data to develop strategies for our products that serve millions of customers and thousands of merchants.

Build, validate, deploy, and monitor robust, scalable machine learning models and model pipelines across the risk lifecycle, including onboarding, affordability, life‑time value, credit/default risk, in‑life risk, collections, and fraud.

Present complex data science findings and methodologies to senior stakeholders clearly and concisely.

Apply machine learning methods to solve risk and product‑related business problems and enhance our decision‑making processes.

Contribute to the team’s coding efforts, ensuring best practices in version control, testing, CI/CD, model deployment, monitoring, methodologies, workflows, and tooling.

Conduct A/B testing, champion/challenger testing, and experimental analyses to evaluate new features, risk strategies, model changes, and product changes.

Partner closely with engineering and platform teams to operationalise models, automate workflows, and improve model reliability in production.

What We’re Looking For.

3+ years of hands‑on experience as a data scientist, with a focus on building and deploying models to enhance the customer product experience, risk decisioning, and business outcomes, ideally within credit risk, collections, fraud, financial services, lending, payments, or another decision‑intensive domain.

Proficiency in SQL, Python and core data science and machine learning libraries, such as NumPy, Pandas and Scikit‑Learn.

Strong practical experience with machine learning model development, deployment, monitoring, and iteration in production environments, including cloud‑based model training, archiving, serving, endpoint deployment, and tools such as Amazon SageMaker or similar.

Experience communicating complex ideas to non‑technical audiences and senior stakeholders.

Strong understanding of machine learning methods, their application in real‑world scenarios and a keen awareness of their limitations.

A strong engineering mindset, with the ability to write clean, maintainable, production‑ready code, use version control systems such as Git, and collaborate effectively in a multi‑developer environment.

A results‑driven approach, with the ability to quickly iterate and improve models in production.

Knowledge of AI safety considerations, such as bias detection, privacy management, and handling personally identifiable information (PII).

Familiarity with software development best practices and continuous integration/continuous delivery (CI/CD) pipelines, such as GitHub Actions.

Experience using DBT for data modelling and Looker for BI reporting.

An interest in staying up to date with evolving technologies and applying them to enhance business outcomes.

Nice to Have.

The following are bonuses rather than strict requirements. We do not expect candidates to have all of them:

Prior experience in credit risk modelling, collections optimisation, fraud detection, or risk strategy.

Familiarity with risk model governance, explainability, fairness, affordability, or regulatory considerations in financial services.

Experience with decision science, automated decisioning systems, decision engines, or risk strategy implementation.

Experience applying neural networks or deep learning approaches to practical risk, fraud, or decisioning problems.