Senior Analytics Engineer (Antifraud)

Sumsub; United States; Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Remote-first

Flexible hours

Office access in some locations

Job summary

Sumsub is seeking a data analytics engineer to build the analytical data foundation used to measure and improve fraud detection. This hands-on role combines data modeling with investigation: you will create reliable datasets, assess how detection performs across products and scenarios, and explain results to product teams and clients.

You will design and maintain fraud analytics models with dbt and ClickHouse, ensure data quality, and collaborate with data engineering, product, and fraud

Qualifications

• Experience building analytics data models with testing, documentation, and incremental approaches.
• Experience with ClickHouse or a columnar data warehouse.
• Strong Python skills for data analysis.

Responsibilities

• Design and maintain fraud analytics models using dbt and ClickHouse, or comparable tools and warehouses.
• Create documented datasets and shared metrics that let teams compare detection performance consistently.
• Own data quality through tests, lineage, documentation, and monitoring.
• Work with data engineering, product, and fraud specialists to integrate new data sources.
• Evaluate detection changes across products, clients, and fraud scenarios; turn findings into actionable recommendations.
• Develop repeatable ways to assess detection logic and help investigate complex, data-intensive client cases.

Skills

Analytics data modeling

dbt-style testing

Documentation

Incremental models

Code review

Python

Detection evaluation metrics

Tools

ClickHouse

Job description

Role overview

Build the analytical data foundation used to measure and improve fraud detection. This hands-on role combines data modeling with investigation: you will create reliable datasets, assess how detection performs across products and scenarios, and explain what the results mean to product teams and clients.

Responsibilities

• Design and maintain fraud analytics models using dbt and ClickHouse, or comparable tools and warehouses.
• Create documented datasets and shared metrics that let teams compare detection performance consistently.
• Own data quality through tests, lineage, documentation, and monitoring.
• Work with data engineering, product, and fraud specialists to integrate new data sources.
• Evaluate detection changes across products, clients, and fraud scenarios; turn findings into actionable recommendations.
• Develop repeatable ways to assess detection logic and help investigate complex, data-intensive client cases.

Requirements

• Strong experience building and maintaining analytics data models, including dbt-style testing, documentation, incremental models, and code review.
• Practical experience with ClickHouse or another columnar warehouse and large event-level datasets.
• Strong Python skills for analysis and data work.
• Understanding of detection evaluation, including confusion matrices, precision and recall, PR/ROC curves, thresholds, and error costs.
• Good judgment when working with imperfect data; able to identify bias, leakage, and misleading metrics.
• Able to communicate findings clearly to product and client audiences, with fluent English; experience using AI tools in analytics or data engineering, or readiness to adopt them.

Benefits and work setup

Remote-first work with flexible hours and optional office or coworking access in some locations. Time off includes a birthday holiday, 10 personal days annually, seven sick days without paperwork, and additional time around Christmas and New Year. Compensation is market-benchmarked and varies by confirmed work location.