Data Scientist

Data Scientist

Multitude

Vilnius or Berlin

Role Overview

We are looking for a Data Scientist to build and deploy end-to-end machine learning solutions that power key fintech use cases such as credit risk modeling, customer lifecycle optimization, fraud detection, and collections strategies.

This is a role where your work directly influences key business decisions across risk, growth, and collections. As a Data Scientist, you’ll operate at the intersection of data, product, and engineering—developing scalable, production-level machine learning solutions in a modern Azure ML environment. You will take ownership of the full ML lifecycle, from problem definition to deployment and monitoring, while collaborating closely with stakeholders to turn data into insights that drive real, measurable impact.

Key Responsibilities

• Own the full lifecycle of machine learning solutions: problem framing, data exploration, feature engineering, model development, deployment, and monitoring;
• Develop and productionize models for credit scoring, marketing optimization, collections, and other core business problems;
• Work with large-scale data to build robust data pipelines and feature datasets;
• Deploy and manage models using Azure Machine Learning, including experiment tracking, model versioning, and lifecycle management;
• Collaborate closely with stakeholders (product, risk, marketing, engineering) to identify high-impact opportunities and translate them into data solutions;
• Design, implement, and analyze A/B tests and experiments, ensuring statistically sound and business-relevant conclusions;
• Build monitoring frameworks to track model performance, detect data/model drift, and ensure long-term reliability;
• Ensure models meet regulatory and explainability requirements (e.g., credit decision transparency);
• Communicate insights and model behavior clearly to both technical and non-technical stakeholders.

Requirements

• Degree in Data Science, Statistics, Mathematics, Econometrics, or a related field;
• Strong programming skills in Python and SQL (R is a plus);
• Solid understanding of machine learning techniques and their practical trade-offs;
• Experience with Azure Machine Learning or similar platforms (AWS SageMaker, GCP Vertex AI);
• Experience deploying models into production and maintaining them (monitoring, retraining, versioning);
• Strong knowledge of experimentation and statistical methods (A/B testing, hypothesis testing);
• Experience with model explainability techniques (e.g., SHAP, LIME), especially in regulated environments;
• Ability to translate complex analyses into clear business insights;
• Fluent in English.

Nice to Have

• Experience in fintech domains such as credit risk, fraud detection, or collections optimization;
• Experience working with distributed data processing frameworks (e.g., Apache Spark, Databricks);
• Familiarity with MLOps practices (CI/CD, model registries, pipeline orchestration);
• Experience with feature stores and production data pipelines;
• Experience working in regulated environments (e.g., GDPR, model validation standards).