Senior Data Scientist - Fraud
Veriff
Job Overview
Who's the hiring manager?
Sign up to PitchMeAI to discover the hiring manager's details for this job. We will also write them an intro email for you.

Job Description
About The Role
Veriff pursues the mission of creating a safer, more secure world by establishing trust online. The Fraud Engineering team contributes directly to this mission by developing the systems and models that identify and stop fraudsters before they succeed.
We are building the next-generation fraud detection platform, designed to evolve, scale, and stay ahead of sophisticated fraud threats. This position offers the opportunity to contribute to the foundation of that system.
We seek a Senior Data Scientist - Fraud who thrives on complex challenges, understands real-world fraud dynamics, and delivers measurable impact. The successful candidate will collaborate with fraud analysts, engineers, and product managers to develop models, uncover fraud patterns, and integrate their work into production environments at scale.
Responsibilities
- Help design and evolve fraud detection mechanisms underpinning Veriff’s next-generation fraud detection platform.
- Build and refine real-time models to identify and block fraud before it impacts customers.
- Invent new detection strategies that outpace fraudsters and adapt to shifting attack vectors.
- Design and validate data-driven hypotheses to identify emerging fraud patterns, and transform them into scalable detection features and model improvements.
- Collaborate with engineers to deploy and scale models within production systems.
- Define model monitoring strategies, assess business impact, and iterate based on results.
- Investigate the latest advances in fraud analytics and applied machine learning.
Requirements
- Minimum of 7 to 8 years' experience as a Data Scientist.
- Familiarity with production deployment of machine learning models.
- Proficiency in Python and SQL.
- Strong capabilities in data manipulation and visualisation using tools such as Pandas/Polars, NumPy, and Matplotlib/Seaborn.
- Practical experience with machine learning frameworks such as scikit-learn, XGBoost/LightGBM/CatBoost.
- Solid understanding of both supervised and unsupervised learning techniques.
- Ability to communicate findings clearly with technical and non-technical stakeholders.
Desirable
- Experience within fraud detection, financial crime, trust and safety, or related domains.
- Experience working with embeddings and vector similarity search.
- Experience working in cloud environments, such as AWS, GCP, or Azure.
Why Join Veriff?
At Veriff, team members contribute to meaningful outcomes with real-world impact. We value trust, accountability, and practical excellence. Our environment supports personal growth and provides the tools required to succeed.
What We Offer
- Flexibility to work remotely or from our modern offices.
- Four additional recharge days annually, in addition to regular leave.
- Stock options, allowing you to share in the company's success.
- Comprehensive private health insurance.
- Personalised Learning & Development and Health & Sports budgets.
- Relocation support when moving to Estonia.
Key skills/competency
- Fraud Detection
- Machine Learning
- Python
- SQL
- Real-time Modeling
- Data Manipulation
- Model Deployment
- Risk Management
- Supervised Learning
- Unsupervised Learning
How to Get Hired at Veriff
- Research Veriff's culture: Study their mission, values, recent news, and employee testimonials on LinkedIn and Glassdoor, focusing on their commitment to online trust and fraud prevention.
- Tailor your resume: Customize your resume to highlight experience in fraud detection, real-time machine learning, and production deployment of models, using keywords like Python, SQL, and ML frameworks.
- Showcase practical experience: Prepare to discuss specific projects where you designed, built, and scaled fraud detection models, emphasizing measurable impact and collaboration.
- Prepare for technical deep-dives: Brush up on advanced data manipulation (Pandas, NumPy), machine learning frameworks (scikit-learn, XGBoost), and both supervised and unsupervised learning techniques.
- Demonstrate problem-solving: Be ready to articulate how you've identified emerging fraud patterns, validated hypotheses, and adapted detection strategies to complex, evolving threats.
Frequently Asked Questions
Find answers to common questions about this job opportunity
Explore similar opportunities that match your background