Data Scientist -Search

About Wallapop

Wallapop is a Barcelona-based scale-up driven by the purpose to empower people to embrace a more conscious and human way of consumption. We believe in a world where collaborative economy is mainstream. This is what drives us💫.

Wallapop operates in Spain, Italy, and Portugal, offering a catalogue of several hundreds of millions of products and services. Powered by technical innovation and continuous improvement, we bring together the scale & trust of classifieds with the marketplace’s convenience & reach. Our mission is to enable a connected trade ecosystem, making 2nd-hand the norm through smart use of technology.

The Challenge 🧩

Our platform generates vast amounts of data. With a mature infrastructure already in place and a growing team, the opportunities to make a tangible impact are endless. As a Data Scientist, you will improve marketplace dynamics by working on end-to-end ML solutions—from data gathering and prototyping to deployment and iteration.

As a Data Scientist at Wallapop, you will be working on Data Science and Machine Learning initiatives aimed at improving the whole marketplace dynamics. This will include topics such as improving models that power users' main interaction point: Search. You will also look into various models that will help users discover new items through ranked Recommendations, Similar Items, and more.

You will work closely with other Data Scientists, Product Managers, Engineers, UX Researchers, and Analysts to understand the product requirements and explore possible data and ML solutions. You will own the whole product lifecycle, from gathering the data needed to prototyping, building, evaluating, and iterating end-to-end solutions, all within Wallapop’s Data and ML Platforms.

Additionally, you will have the opportunity to work on internal research projects, exploring new technologies and building PoCs that could ultimately become data products or insights, and be valuable for Wallapop.

What You Will Do 👇

• Collect, clean, and analyze large datasets from diverse sources, including user behavior, transactions, and market trends.
• Develop and implement machine learning models to solve business problems, such as personalized recommendations and search.
• Work with multidisciplinary Product teams to identify opportunities and gather requirements (both in terms of product and tech).
• Own initiatives from start to deployment: ideation, data processing (ETL), modeling, testing, deployment, monitoring, and iteration (w/ help from Engineering partners).
• Proactively suggest, research, and prototype new ideas for data and ML solutions.
• Communicate complex data insights to both technical and non-technical audiences, including stakeholders involved in marketplace operations.

What We’re Looking For 🔍

• Experience working with Search, recommendations & Ranking models in production environments.
• Problem-Solving Core: A degree in a quantitative field (Engineering, Math, Stats, Physics) or equivalent practical experience in data science.
• Software Mindset: Proficiency in Python and the ability to write clean, maintainable code for ML applications.
• Production Experience: A proven track record of building and deploying data products that solve business challenges in a production environment.
• Data Fluency: Advanced SQL skills and experience handling large datasets (knowledge of libraries like Pandas or Scikit-learn is highly valued).
• Growth Orientation: A desire to learn new technologies and an ability to adapt your technical approach to the problem at hand.
• Algorithmic Foundation: Solid understanding of Machine Learning fundamentals, specifically as they apply to personalization or recommender systems (e.g., collaborative filtering, content-based filtering, or deep learning for embeddings).

What Would Be A Plus 🚀

• Experience working within an eCommerce or Marketplace platform, or in a product-tech company.
• Experience working within the Logistics, Trust & Safety or Customer Service domains.
• Experience working within the AWS cloud (Redshift, S3, Lambda), and with cloud MLaaS solutions such as Amazon SageMaker (preferably), but also Google Vertex AI, Microsoft Azure ML, and other MLOps tools (MLFlow, Flyte, Feast, Kubeflow, etc).