Analytics Engineer

Role overview Strengthen the data foundation used to assess fraud prevention systems. This hands-on role combines analytics engineering and performance analysis: you’ll build reliable models and metrics, then use them to evaluate detection outcomes and communicate useful findings to product teams and clients.

Responsibilities - Develop and maintain core fraud analytics data models using dbt and ClickHouse or comparable tools. - Create documented datasets and shared metrics that make detection results consistent and comparable. - Own data quality through tests, documentation, lineage and monitoring. - Work with data engineering, product and fraud specialists to incorporate new sources. - Analyze detection performance across products, clients and fraud scenarios, and establish repeatable evaluation methods. - Explain results and recommendations clearly to technical and non-technical stakeholders.

Requirements - Production experience with dbt or an equivalent modeling tool, including tests, documentation, incremental builds and code review. - Experience with ClickHouse or another columnar warehouse and large event-level datasets. - Strong Python skills for analytics and data work. - Knowledge of detection evaluation, including precision and recall, confusion matrices, ROC and PR curves, threshold trade-offs, and error costs. - Good judgment with imperfect data, including the ability to detect bias, leakage and misleading metrics. - Clear communication with product stakeholders and clients, fluent English, and experience or readiness to use AI tools in data work.

Benefits and work setup Remote-first work with flexible hours and no mandatory office attendance; coworking or office options may be available in some locations. Time off includes a birthday holiday, ten personal days each year, seven sick days without paperwork and additional winter holiday time. Compensation is market-based and varies by confirmed work location, with details provided during recruitment.