Remote
Data Scientist
About this role
Founded in 2003 and headquartered in Singapore, Group-IB is a leading creator of cybersecurity technologies to investigate, prevent, and fight digital crime. Combating cybercrime is in the company’s DNA, shaping its technological capabilities to defend businesses, citizens, and support law enforcement operations. Group-IB’s Digital Crime Resistance Centers (DCRCs) are located in the Middle East, Europe, Central Asia, and Asia-Pacific to help critically analyze and promptly mitigate regional and country-specific threats.
These mission-critical units help Group-IB strengthen its contribution to global cybercrime prevention and continually expand its threat-hunting capabilities. ABOUT THE ROLE In this role, you will be instrumental in the engineering and end-to-end development of analytical services designed to provide advanced fraud intelligence. You will leverage your experience in production-grade Python development to enhance our strategic fraud detection capabilities through the analysis of session and network data, development of sophisticated fraud detection logic, and implementation of predictive modeling and scoring methodologies across diverse web entities.
YOUR MISSION Execute data collection and analysis from disparate sources to establish and maintain robust ETL pipelines. Perform advanced research into methodologies for fraud mitigation and anomaly detection within transactional and sessional data environments. Develop and integrate machine learning models and mathematical algorithms into the Fraud Protection ecosystem. Engineer and validate AI Agents tailored for complex analytical operations.
Analyze session and network data to develop sophisticated fraud detection logic. Implement predictive modeling and scoring methodologies across diverse web entities. Synthesize research findings into comprehensive documentation and formal presentations. WHAT WE ARE LOOKING FOR Strong foundation in tabular data analysis. Experience writing production-ready, asynchronous Python code (Python 3.10+). Experience with Python data analysis and machine learning libraries, including pandas and scikit-learn.
Proficiency with Git; experience with Docker is a plus. Proficiency in IDE and terminal-based development. Experience building ETL pipelines. Experience orchestrating AI coding agents efficiently. Research-oriented mindset. Database experience with Elasticsearch, Cassandra, or ClickHouse is highly preferred. WHAT SETS YOU APART Prior experience within the cybersecurity or anti-fraud sectors. Experience implementing AI agents end-to-end.