Job Description

We are working towards transforming the whole Allegro front-end experience based on Product Catalog by achieving highest quality content, images and product groups. As we’re working with more than 100 million products we need scalable solutions. Our team of data scientists is building Machine Learning models and algorithms that drive the product catalog development and ultimately our business.

As a Data Scientist, you will build and maintain ML models needed to develop the catalog. You will be responsible for training models, monitoring their performance, diagnostics and improving the business metrics. Our team uses different kinds of models and tech to bring direct business impact. Our current projects include:

• Detection of product duplicates
• Detection of misclassified products
• Clustering and grouping products
• Face anonymization solution

Technologies you’ll encounter on the job are (among others): Python, Airflow, Big Query, GCP, Spark, VertexAI, Looker Studio.

Why is it worth working with us, and what sets us apart?

• We are a team that is not afraid of hard problems and is constantly looking for development opportunities. We have a track record of deploying our models at a large scale and focus on bringing the impact on production. With a wide variety of projects you’ll never be short of interesting challenges.
• You will use some of the most interesting datasets on the market that are just waiting for you to get even more business value out of them. You’ll work with tabular, natural language, image and time series data.
• You will combine multiple data sources, domain knowledge, and advanced ML techniques to deliver high-quality models.
• Our employees regularly attend conferences in Poland and abroad (Europe & US), and each team has its own budget for training and study aids. If you want to keep growing and share your knowledge, we’ve got you covered.

Our offer is addressed to people who:

• Have experience working independently as a Data Scientist or in a similar role
• Are able to process data and create machine learning models in Python (e.g., scikit-learn, pytorch, tensorflow, xgboost, catboost, light-gbm, pandas)
• Know and understand machine learning algorithms and can apply them in practice, and are willing and able to learn emerging algorithms
• Have a strong command of SQL and experience or interest in analytics within the GCP/Hadoop ecosystem
• Can communicate clearly with business units - from formulating the problem to presenting results in a clear and intuitive way
• Have a researcher's mindset, able to break down complex problems into manageable parts and model them effectively
• Have a strong desire to learn and expand their knowledge
• Are proficient in English (B2) and Polish (C1)

We offer:

• High impact and opportunity to design the ML backbone of largest eCommerce platform in Poland and one of largest in Europe
• Multidisciplinary nature of work at the intersection of business and technology, development opportunities in designing cutting edge solutions at scale that bring real value to customers
• Possibility to implement ML solutions which are unique on the market
• Support of experienced Data Scientists and Engineers - there is always someone to exchange ideas with because we have the best specialists and experts in their field on board
• Well-located office (with fully equipped kitchens and bicycle parking facilities) and excellent working tools (height-adjustable desks, interactive conference rooms)
• A wide selection of fringe benefits in a cafeteria plan – you choose what you like (e.g. medical, sports or lunch packages, insurance, purchase vouchers)
• Annual bonus of 10% of the gross annual salary (depending on your end-year assessment and the company's results)
• Long-term discretionary incentive plan based on Allegro.eu shares
• Fully sponsored English classes, related to the specific nature of your job

Do you want to get to know us better? Listen Allegro Podcast

Send in your CV and see why it is #dobrzetubyć (#goodtobehere)