About the role
Samba is a media intelligence company. As a Junior Data Scientist at Samba in Amsterdam, you will own end-to-end delivery of significant data science projects with minimal guidance.
You are a reliable, autonomous contributor with deep expertise in at least one domain — Identity and audience modelling — and the technical range to build production-ready solutions using modern ML and AI methodologies. You'll work closely with peers, product, and engineering.
Own end-to-end delivery of significant data science projects from problem scoping to production deployment. Make sound, independently-reasoned methodological decisions with clear documentation. Lead solution design for initiatives; break down epics into well-scoped user stories with acceptance criteria; adopt DataOps/MLOps practices. Implement advanced ML workflows including entity resolution, probabilistic linkage, embedding-based matching, semantic similarity and LLM-augmented pipelines. Develop and maintain reusable tools, libraries, and documentation; conduct code reviews with constructive feedback. Collaborate with product, engineering and operations; translate requirements into technical specs; design scalable pipelines. Bachelor's degree required in a quantitative field; Master's strongly preferred. 2+ years of hands-on data science experience with independent delivery of multi-sprint projects. Advanced Python with production-quality code, testing and documentation; strong SQL and PySpark for large datasets. Databricks workflows, Delta Lake, and job orchestration; working knowledge of cloud platforms (AWS or GCP). Solid command of core ML — regression, classification, clustering, evaluation, and experimental design. Proficiency with MLOps: experiment tracking and reproducible deployment. Exposure to modern AI methodologies: RAG, LLM-augmented models, vector databases, semantic search. Strong communication to translate technical work into docs, user stories and cross-functional talks. Mentor junior data scientists and contribute to team standards.