Junior Fraud Data Scientist

Checkout.com; Greater London; On-site; GBP 40,000 - 55,000; Full time

Job summary

Checkout.com in London is looking for a Junior Fraud Data Scientist to join the data team and help protect the platform from financial threats. You will work under senior data scientists in a data-rich environment to identify anomalous behavior and support detection coverage.

You will build features, assist in model tuning, develop dashboards, and collaborate with Fraud Analytics and Product teams to translate insights into automated risk solutions.

Qualifications

• 1–2 years of hands-on data science or data analysis experience.
• Strong Python (Pandas, NumPy) and SQL skills.
• Experience with Databricks and BigQuery.
• Degree in a quantitative field.
• Ability to communicate findings in English.
• Understanding of business impact of data decisions.

Responsibilities

• Exploratory data analysis to identify fraud patterns and anomalies.
• Support model development and optimization under senior data scientists.
• Generate features from structured and unstructured data.
• Build dashboards and monitor model health and data drift.
• Collaborate with Fraud Analytics and Product teams to automate data solutions.

Skills

Python

Pandas

NumPy

Scikit-Learn

SQL

EDA

Model Evaluation

English Communication

Education

Degree in CS/Statistics/DS

Tools

Databricks

BigQuery

MLflow

Airflow

Job description

About the Role

As a Junior Fraud Data Scientist, you will contribute to our ongoing efforts to protect our ecosystem from financial threats and abuse. Working under the guidance of senior team members in a data‑rich environment, you will assist in identifying malicious behaviors, support detection coverage, and help maintain our automated mitigation strategies.

What You Will Be Doing

• Exploratory Data Analysis: Support the team by mining behavioral and transactional datasets to help identify anomalies and emerging fraud patterns.
• Model Support & Optimization: Assist in building, tuning, and validating machine learning models (e.g., XGBoost, LightGBM) under the supervision of senior data scientists.
• Feature Generation: Extract, engineer, and prepare new data features from structured and unstructured sources to help improve model performance.
• Dashboarding & Monitoring: Build and maintain internal dashboards and pipelines to track model health, data drift, and key fraud KPIs.
• Cross‑functional Collaboration: Work alongside Fraud Analytics and Product teams to help translate operational fraud insights into automated data solutions.

Requirements

• Experience: 1––2 years of hands‑on professional experience as a Data Scientist or Data Analyst in a data‑intensive environment.
• Data Science Tech Stack: Solid proficiency in Python (Pandas, NumPy, Scikit‑Learn) and strong capability writing and optimizing SQL queries.
• Modern Data Infrastructure: Exposure to or basic hands‑on experience working within environments like Databricks and data warehouses like BigQuery.
• Academic Background: Degree in a quantitative field (Computer Science, Statistics, Data Science, Industrial Engineering, or equivalent).
• Business‑Impact Focus: An understanding of how to look past raw model metrics (precision/recall) to appreciate the operational impact of data decisions.
• Communication: Fluent English with the ability to communicate technical findings clearly to team members.

Bonus Points

• Prior exposure to or hands‑on projects involving machine learning models in a live, real‑time production environment.
• Familiarity with MLOps or orchestration tools such as MLflow or Airflow.
• Previous domain exposure in FinTech, e‑commerce, payments, or trust & safety.