As a Product Data Scientist, you’ll work as part of a cross-functional team alongside product managers, designers, and software and analytics engineers, using data and your analytical expertise to influence the strategy of our Operations and Compliance products. You’ll focus on two main domains: AML Transaction Monitoring, where you will help optimize our rules‑engine and scale predictive automation, and Merchant Care, where you will measure tooling efficiency and apply text analytics to drive product roadmaps.
You’ll help define how we measure the success of our products, collaborate with engineers on data collection, build analytical frameworks, and run insights to find product improvement opportunities. Data Analytics at Checkout.com is a highly visible function that critically impacts the company’s success. As part of this group, you’ll have a strong support network of Senior Data Scientists, Analytics Engineers, and Data Product Managers to help you develop your technical and data science practice.
How You’ll Make an Impact
- Efficiency & Product Measurement: Build frameworks to measure the operational efficiency and ROI of new software releases and internal tooling updates within Merchant Care.
- Data Partnerships: Work closely with Data Analytics Engineers and Software Engineers to ensure we log and model the right data to produce high‑integrity business insights.
- Data-driven automations and solutions:
- Run historical data simulations to analyze how changes in our deterministic AML rule thresholds affect review backlogs, and suggest optimal logic updates to our SQL‑based alerts.
- Support the development and testing of a Level 1 (L1) automated discounting agent for transaction monitoring alerts, building on existing team frameworks.
- Text Analytics & Insights: Use clustering techniques and LLM‑based summary extraction on merchant ticket conversations to identify recurring user friction points and help product teams map future features.
What We’re Looking For
- Technical foundations: Excellent data interrogation skills with SQL and the ability to comfortably write, read, and iterate through Python scripts to run data science analyses.
- Foundational ML knowledge: A good understanding of foundational data science concepts (e.g., statistics, clustering, basic NLP workflows). You do not need experience deploying ML models to production, but you should understand how to apply them to data tasks.
- Analytical Mindset: A strong analytical mind with a demonstrable ability to take operational problems and convert them into structured, data‑informed solutions.
- Communication: Clear and precise communicator, able to explain data insights and analytical logic to non‑technical stakeholders (Product Managers and Operations teams).
Experience: Prior experience or a strong internship background in product analytics, risk/compliance data, or a high‑growth tech environment is a plus.
Hybrid working model offers flexibility, with three days per week in the office to support collaboration and connection.
#J-18808-Ljbffr…