Expert Fraud Data Scientist
Description
The Artificial Intelligence Tribe at BNP Paribas Fortis aims to create an efficient and seamless banking experience for customers while empowering employees through AI. Its team of approximately 90 experts includes Data Scientists, Machine Learning Engineers, Business Analysts, Scrum Masters, Product Owners and Managers. The tribe develops virtual assistants, advanced AI tools for employee efficiency and creativity, and automation for internal processes. This assignment adds an expert fraud-focused Data Scientist to that multidisciplinary environment.
The role focuses on making better use of transactional, customer and behavioral data for fraud detection. You will collect, label, curate, structure, enrich and engineer data and features, then design and continuously improve fraud models. The analytical toolkit includes supervised and unsupervised machine learning, anomaly detection, graph analytics, network analysis and behavioral analytics. The work also includes turning large data volumes into actionable fraud intelligence and deploying AI applications in production.
You will collaborate closely with Fraud Operations, Risk, Compliance and Product teams to identify emerging fraud trends and translate business needs into scalable analytical solutions. You will investigate complex fraud schemes, uncover new attack vectors and proactively develop detection strategies that reduce financial and reputational risk. The position calls for substantial data science and AI application experience, strong Python and large-scale data-processing expertise, and fluent English alongside the listed Dutch and French language requirements. It also values business orientation, communication and influencing skills, analytical synthesis, autonomy, commitment, perseverance and the ability to work in a dynamic multicultural environment.
Top Reasons to Apply
High-impact fraud AI
Advanced analytics stack
Multidisciplinary AI tribe
Cross-functional business exposure
Long-term expert mission
Detailed Responsibilities and Skills
General skills
- At least 7 years of experience in data science, preferably in the financial sector, with a focus on fraud detection; candidates with less experience may still be considered if they have strong academic credentials.
- A minimum of 5 years of experience developing AI applications.
- Background in fraud detection.
- At least a Master's degree in a quantitative field such as statistics, computer science or engineering; candidates from other academic backgrounds with strong analytical skills are also welcome.
- Strong analytical skills.
- Dutch is listed as a language requirement; no proficiency level is specified.
- French is listed as a language requirement; no proficiency level is specified.
- Fluent English.
- Team player.
- Business oriented.
- Quick self-starter with a proactive attitude.
- Good communication and influencing skills.
- Good analytical and synthesis skills.
- Autonomy, commitment and perseverance.
- Ability to work in a dynamic and multicultural environment.
- Financial-sector data science experience is preferred.
- A Master's degree with a focus on fraud detection is preferred.
- A PhD is a plus.
Technical skills
- Strong hands-on experience manipulating and processing large-scale datasets.
- Skilled at collecting, enriching, structuring and validating complex transactional and behavioral data for fraud analytics and machine learning initiatives.
- Experience with supervised machine learning.
- Experience with unsupervised machine learning.
- Experience with anomaly detection.
- Experience with graph analytics.
- Experience with network analysis.
- Experience building data-centric AI solutions using robust software engineering practices, high-quality datasets and state-of-the-art modeling approaches to detect, investigate and prevent fraud.
- Experience contributing to deployment of AI applications in production using a comprehensive stack of tools.
- Extensive Python programming experience.
- Experience with generative AI is a plus.
- Java experience is a plus.
Tools
- Strong hands-on SQL experience for large-scale data manipulation and processing.
- Strong hands-on Python and Pandas experience for large-scale data manipulation and processing.
- Strong hands-on Spark/Hadoop experience for large-scale data manipulation and processing.
- Experience with distributed data processing technologies.
- Extensive Python programming experience.
- Java experience is a plus.