Senior Data Scientist

Posted 9hrs ago

Employment Information

Education
Salary
Experience
Job Type

Report this job

Job expired or something wrong with this job?

Job Description

Senior Data Scientist developing LLM, NLP, and GNN solutions for a major European e-commerce platform. Scaling Product Knowledge Graphs from proof of concept to production.

Responsibilities:

  • Design, train, and evaluate models based on Large Language Models (LLMs), Natural Language Processing (NLP), or Graph Neural Networks (GNNs)
  • Build concept graphs, establish concept hierarchies, and map them to a product catalog containing millions of items
  • Scale data processing pipelines and generate vector representations, including product and concept embeddings, for downstream applications such as recommendation systems
  • Conduct iterative experiments, including reviewing state-of-the-art research, defining evaluation metrics, refining prompts, and calibrating annotated datasets
  • Prepare solutions for production deployment in close collaboration with engineering teams, including readiness for A/B testing
  • Support the R&D team in developing and scaling a Product Knowledge Graph solution from PoC to full-scale production within a large e-commerce platform

Requirements:

  • Minimum 4–5 years of commercial experience as a Senior Data Scientist or Machine Learning Research Engineer, working on large-scale data projects
  • University degree in Computer Science, Mathematics, Statistics, Physics, or a related STEM field
  • Proven experience in end-to-end research and development projects, from reviewing state-of-the-art (SOTA) research and formulating hypotheses to designing experiments, conducting offline/online validation, and delivering production-ready solutions
  • Hands-on experience with modern Natural Language Processing (NLP) techniques and Large Language Models (LLMs), including prompt engineering, information extraction, synthetic data generation and cleaning, semantic clustering, and working with Transformer-based models and Sentence Encoders
  • Strong proficiency in Python and the ML/DL ecosystem, including PyTorch or TensorFlow, Hugging Face Transformers, Pandas, NumPy, and Scikit-learn
  • Ability to write clean, testable, production-quality code and work with CI/CD pipelines
  • Advanced SQL skills, including analytical SQL for large datasets
  • Experience processing data in cloud environments, particularly Google Cloud Platform, BigQuery, Vertex AI, and Vertex AI Pipelines
  • English level min. B2+
  • Nice to have: Experience in designing, building, or working with Knowledge Graphs, graph databases, and Graph Neural Networks (GNNs)
  • Nice to have: Experience in processing data at massive scale or developing low-latency ML systems with response times measured in tens of milliseconds, such as search or recommendation systems
  • Nice to have: Strong understanding of modern recommendation system architectures, including Two-Tower models, retrieval, ranking, complementary product recommendations, or semantic search solutions (ANN / vector search)
  • Nice to have: Experience in designing and managing data annotation processes, including collaboration with annotation teams, refining annotation guidelines, and evaluating data quality and consistency

Benefits:

  • Enriching and collaborative environment that fosters your growth at every step