DATA SCIENTIST (PYTON, PANDAS/POLARS, SPARK, OOP, SQL)

For our client in Amsterdam, we are looking for a Data Scientist (Pyton, Pandas/Polars, Spark, OOP, SQL)

The role

You will join the squad, working alongside engineers and a product owner. Your main responsibility will be to improve and extend our transaction classification models to enhance the automatic loan approval process. You will also work on monitoring model performance and collaborate closely with engineers, analysts and business stakeholders to create the best customer experience.

Our work is supported by weekly Kanban sessions to align tasks and priorities.

Your profile

• Master’s degree in Data Science, Computer Science, Econometrics or a related field

• Experience with Python, pandas/polars, Spark, OOP, SQL, test driven development, model development, model monitoring, and software engineering best practices

• Strong analytical skills and attention to detail

• Excellent communication skills; able to explain complex analyses clearly

• Strong stakeholder management skills

• Proficiency in Dutch

Nice to have

• Experience with CI/CD, deployments and Docker

• Experience with GCP

• Strong engineering skills

• Familiarity with transactional and customer-level data

• Experience in Consumer Lending domain or knowledge of credit processes

Tech stack

• Languages & data: Python, SQL

• Development environment: VSCode, terminal

• Versioning & CI/CD: Azure DevOps (Repos, Pipelines)

• Containerization: Docker

• Data & Observability: Elastic, Grafana

• ML Platform: MLflow, DAP/MLP (internal platforms)

• Orchestration: Airflow

• APIs: consuming REST APIs