Junior Data Scientist

WELCOME TO OLX

At OLX, we work together to build a more sustainable world through trade.

We make it safe, smart, and convenient to buy and sell cars, find housing, get jobs, buy and sell household goods, and more. Our colleagues around the world help to serve millions of people around the world every month, through its well-loved consumer brands including OLX, Otodom, Auto Trader, Property
24.

We are hiring a Junior Data Scientist for our Trust and Safety team. In Trust and Safety, our mission is to protect the OLX community from harmful or inappropriate experiences, ensuring that our users can buy, sell and connect with confidence, whether they are searching for their next item or their next job on our platforms.

We invite you to join a team that works with our consumer platforms across the entire EU region. A team that breaks through walls and builds cross-functional connections with everyone around. A team where a common mission and goals matter more than reporting lines. We build on each other, asking for help and support when needed, and we proactively support others.

In your day-to-day routine, you will have the opportunity to work on supervised models for behavioral classification, deep learning models for image classification, regression models for value estimation, as well as NLP and LMM-based models for various applications. All using Python and the AWS cloud. You will be exposed to key stakeholders, have direct contact with internal customers. You will have carte blanche to experiment and test things.

And most importantly, you will also witness how your work impacts the day-to-day business of our customers.

• Work in the Data Science team from a platform and marketplace perspective.
• You will build models, tinker around them to make them work, test them, and eventually deploy them to production. You will see your stuff in action, and you will be able to measure the true impact of your models (less expected, yet a requirement)
• You will maintain strong relationships with stakeholders. This means asking a lot of questions to business people and translating their requirements into achievable projects. It also means collaborating with other teams, like infrastructure and data engineering, to get things done in an elegant and timely manner.
• Partner with Engineering and Product to deliver solutions (customer-facing and platforms) to our customers (internal and end customers)
• Work with Product Analytics to track the KPIs of different ML use cases and measure the impact on our customers.
• Partner with the Experimentation team to integrate the KPIs and their proxies into the Experimentation (A/B testing) platform.
• You will work in multi-functional teams, in a diverse, multinational environment, filled with people from Portugal, Bulgaria, Romania, Poland, Ukraine, Kazakhstan, and Uzbekistan.
• Most importantly, you will have fun working with us :)

• Located in Poland.
• At least 1 year of professional experience as a Data Scientist.
• Very strong analytical skills. Like really strong! So strong that truth and light are your two middle names.
• Solid background in statistics and modeling.
• Good knowledge of Python, which means having experience with at least one of the following:
  Scikit-Learn, Tensor Flow, PyTorch, or Pandas.
• Very good knowledge of NLP and Deep Learning (Embeddings, Language Models, Transformers, etc.).
• Good knowledge of Generative AI and Large Language Models (LLMs).
• Good understanding of engineering best practices, that is: testing, CI/CD, monitoring, alerting, and containers.
• Hands-on experience with SQL.
• Experience with MLOps.
• Proficient in English with excellent written and oral communication skills!
• Strong presentation skills.
• Able to work in diverse, multi-functional teams with people from different backgrounds.

• Exposure to other programming languages such as Kotlin, Java, Scala, etc
• Experience bringing models into production and serving models at scale
• Experience using AWS for deploying machine learning solutions
• Experience with building data pipelines using tools like Spark and Airflow
• Underst…