We are hiring a Senior Data Scientist in Amsterdam to help shape Samba TV's data science function for the agentic era of advertising. You will define modeling methodology, build production ML systems, and apply modern AI and agentic capabilities across our data products.
You bring 8+ years of experience, deep expertise in machine learning and modern AI, and the technical range to take methodology from research through production deployment. You are an active collaborator with engineering, product, and partner teams, and an advocate for rigorous, defensible modeling practice.
What You'll Do
Own end-to-end delivery of data science projects, from problem scoping through production deployment.
Define and ship modeling methodology that powers Samba's data products, including model selection, evaluation frameworks, and reproducibility standards.
Apply solid command of core ML and statistics (regression, classification, clustering, model evaluation, experimental design, causal inference) to billion-row, real-world data.
Build production-quality Python and PySpark on Databricks: well-tested, documented, reusable.
Partner with Data Engineering to define data requirements, validate pipelines, and ensure model inputs are reliable and production-ready.
AI and Agentic CapabilitiesBuild and operate advanced AI systems using modern methodologies: retrieval-augmented generation (RAG), LLM-augmented modeling and Graph Neural Networks. Design AI-driven modeling approaches that improve as signals evolve, supporting agentic decision-making at platform scale.
Integrate LLMs and agentic workflows into production ML pipelines where they extend modeling capability and unlock new product surfaces.
Technical Contribution and CollaborationDrive technical design for modeling components within your scope, producing clear solution documents covering problem statement, approach, metrics, and trade-offs.
Translate business requirements into modeling solutions in close collaboration with product, engineering, and go-to-market partners.
Uphold high standards for production-quality data science.
Mentor data scientists on the team through structured feedback, pairing, and design review.
MLOps and Production PracticeEstablish and operate MLOps practices: experiment tracking, pipeline orchestration (Airflow), model monitoring, retraining workflows, and reproducibility standards.
Apply privacy-compliant data handling practices, including GDPR, CCPA, and Samba's data governance policies.
Who You Are
8+ years of hands-on data science experience with a Bachelor's degree in Statistics, Data Science, Computer Science, Mathematics, or a related quantitative field (or 6+ years with a Master's, 3+ years with a PhD, or equivalent).
Demonstrated ability to own and deliver complex, multi-sprint data science projects from problem scoping through production deployment.
Solid command of core ML and statistics, including neural networks, regression, classification, clustering, model evaluation, experimental design, and causal inference, applied to billion-row datasets.
Track record of building methodology, not just applying it: data analysis, model selection, evaluation frameworks, and solid documentation of decision processes
Production experience with vector databases (Pinecone, Weaviate, Milvus, pgvector, or equivalent) for retrieval, matching, or inference at scale.
Advanced Python with production-quality, tested code; strong SQL and PySpark on billion-row datasets.
Databricks, Delta Lake, and job orchestration (Airflow); hands-on production experience on AWS, GCP, and Databricks.
MLOps proficiency: experiment tracking, pipeline orchestration, model monitoring, reproducible deployment.
Experience designing and operating agentic AI systems in production: prompt engineering, agent orchestration, tool use, or integration of LLMs into ML pipelines.
A clear communicator who translates technical work into design docs, user stories, and cross-functional conversations.
An active mentor who invests in others, gives direct feedback, and raises the bar for the team as a whole.
PreferredKnowledge graph design (RDF, OWL, SPARQL, or equivalent graph frameworks), Natural Language Processing, Background in ad tech, CTV/OTT, ACR, audience activation, identity resolution, or measurement methodologies.
Experience with causal inference (A/B testing, synthetic control, uplift modeling).
Skills Required
- 8+ years hands-on data science experience (or 6+ with MS, 3+ with PhD or equivalent) and Bachelors in quantitative field
- Proven ability to deliver complex data science projects from scoping through production deployment
- Strong command of core ML and statistics (neural networks, regression, classification, clustering, model evaluation, experimental design, causal inference) applied to billion-row datasets
- Production experience with vector databases (Pinecone, Weaviate, Milvus, pgvector, or equivalent) for retrieval/matching/inference at scale
- Advanced Python with production-quality, tested code; strong SQL and PySpark on billion-row datasets
- Databricks and Delta Lake experience and job orchestration (Airflow); hands-on production on AWS and/or GCP
- MLOps proficiency: experiment tracking, pipeline orchestration, model monitoring, reproducible deployment
- Experience designing and operating agentic AI systems in production (LLM integration, prompt engineering, agent orchestration, tool integration)
- Ability to define modeling methodology, evaluation frameworks, and reproducibility standards; produce clear technical design documents
- Collaborative communicator who translates technical work into design docs, user stories, and engages cross-functionally
- Active mentor who provides structured feedback and technical coaching
- Knowledge graph design (RDF, OWL, SPARQL or equivalent graph frameworks)
- NLP experience
- Background in ad tech, CTV/OTT, ACR, audience activation, identity resolution, or measurement methodologies
- Experience with causal inference methods (A/B testing, synthetic control, uplift modeling)
What We Do
Television remains a vibrant cultural influence and an essential source of entertainment and information worldwide. Tremendous growth in content choices, and viewing platforms that allow us to watch anything, anytime, on any screen, has actually made it harder for viewers to discover and keep up with all the great programming available. It’s also more competitive for content providers to keep your attention, and for marketers to make strong, measurable connections with their target consumers. Technology that improves the viewing experience, enables content discovery, and addresses audience fragmentation across screens will strengthen television’s business model and relevance to consumers. Data is at the center of any solution to make TV better. Samba TV's technology is built into Smart TVs and easily maps to smart phones and tablets. By recognizing what's on screen, Samba TV learns what viewers like and using machine learning algorithms, enables discovery of shows and actors in a whole new way. Likewise, our data and measurement products are transforming the way stakeholders across the media landscape are thinking about their business. Given the dramatic growth in streaming services, connected devices, time-shifting, and multi-screen viewership, our data products solve real problems and create a meaningful competitive advantage for our clients.
