Data Scientist - Product Catalog Data

Allegro is the most popular shopping platform in Poland and the largest e-commerce platform of European origin. It operates a marketplace model with over 135,000 merchants and more than 250 million offers across key categories. The platform reaches 22 million customers monthly, offers fast and free deliveries under Allegro Smart!, and includes modern financial services and a wide pickup network.

• Hands-on experience with Spark or PySpark handling massive datasets
• Practical experience in MLOps and deploying models into production
• Solid software engineering skills in Python with clean object-oriented code and unit tests
• Strong foundations in statistics and machine learning including model selection and evaluation
• Enthusiasm and understanding of Generative AI and Agentic AI principles
• Excellent communication and business sense to translate business challenges into ML problems
• Relevant degree in Mathematics, Physics, Computer Science, Economics, or equivalent experience

Nice to have:

• Experience with Apache Airflow for pipeline orchestration

• Co-create projects at each stage from concept to productization to deliver insights and models solving business problems
• Use a wide range of modeling techniques including gradient boosting, Bayesian methods, causal inference, optimization, deep learning, and Generative AI (LLMs, Agentic AI)
• Collaborate with Data Engineers supporting data processing on GCP
• Work closely with Analysts, PMs, and Developers to ensure seamless integration of solutions
• Leverage diverse data types including spatial data, natural language (NLP), images, and time series
• Participate in implementations of both offline and online models
• Engage in brainstorming sessions, knowledge sharing, and continuous professional development