Remote | Data Scientist (Search)

Key Skills

Java Programming, Python Programming, C++, C Programming, SQL, Cloud computing, Scala Programming, Machine learning techniques, Data science techniques, MATLAB Programming, PyTorch, TensorFlow, R Programming

Job Description

The Data Science team at OLX Group is responsible for building algorithmic solutions to facilitate transactions between buyers and sellers. We are developing personalization technologies and optimization strategies that have a direct impact on OLX’s users as well as the company’s bottom line.

You will be encouraged to research state-of-the-art machine learning, in the areas of search relevance, ranking, recommender systems, and more. Applying these methods to core OLX product platforms deployed in the cloud that are affecting the user experience for millions of visitors per month, rolling your solutions to production, analyzing model results offline and online, and measuring site impact.

Some of the challenges that we are focusing on are maximizing the relevance of the search results by applying ML-based rankers, combining different sources of ads in search and recommendations to optimize the satisfaction of both buyers and sellers, estimating the impact that the interactions generated by the buyers have on the revenue, and detecting trending products even before they become popular.

The Buyer team

The Data Science Buyer team at OLX Group is responsible for unlocking the hidden value for our users by using data and artificial intelligence. Our main goal is to help our customers to find the best products in an efficient and enjoyable way. We have a track record of impactful applications of ML to solve business problems in some of the main user flows and we want to continue expanding the boundaries of what ML is capable of at OLX. 

Our team collaborates with product teams from OLX, as well as the Motors and Real Estate verticals like Otomoto and Otodom, across the entire EU region. This means that our solutions need to scale to millions of data points and may be reused in markets with similar characteristics. We think of experimentation as a tool to learn what our users want. We always start simple and fail fast. This way we can create solutions that can be adapted to every market.

On a typical day, you will be interacting with other members of your cross-functional team. You may collaborate with a data analyst to analyse the results of an A/B test or discuss different alternatives to impact the team’s KPIs with the product manager, or you may have to present your amazing jupyter notebook to other data scientists to collect feedback. In any case, you will find a group of friendly people that wants to collaborate with you to improve the user experience and ultimately have fun together!

What you will be doing:

• Work in multi-functional teams with people from different backgrounds
• Find opportunities where data science will make an impact
• Help to translate business requirements into machine learning models
• Build effective solutions with machine learning
• Bring machine learning services to production together with engineers
• Measure the impact of your models on company goals
• Collaborate with internal and external stakeholders

What are we looking for:

• Strong data analysis and machine learning skills
• At least 2 to 3 years of professional data science experience
• Experience participating in projects related to search relevance and ranking
• Strong engineering background: proficiency in Python and a good understanding of best engineering practices
• Exposure to other programming languages such as Kotlin, Java, Scala, etc
• Experience with at least two of the following machine learning frameworks: Scikit-Learn, XGBoost, TensorFlow, PyTorch, (or similar)
• Hands-on experience in the Python ecosystem for data science 
• Understanding of A/B testing and experimentation
• Proficient in English with excellent written and oral communication skills
• Based in Poland

Nice to have:

• Experience bringing models in 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
• Experience with Solr or Elasticsearch
• Experience with recommender systems
• Exposure to NLP libraries such as spaCy, SparkNLP or BERT
• Exposure to production infrastructure and DevOps practices: monitoring, alerting, CI/CD, container-orchestrating platforms, and infrastructure-as-code tools (Grafana, Prometheus, Kubernetes, Terraform)
• Exposure to MLOps tools

What we offer:

• Permanent contract with 50% KUP.
• Annual bonus of 15% of your base salary.
• Strengths-based personal career development.
• Company mobile phone, MacBook Pro or Windows Dell along necessary accessories to make your work comfortable.
• Competitive compensation and benefits (medical care, sports package and others).
• Training and conference budget.
• The opportunity to learn from each other and become better every day.
• A passionate and diverse team of data scientists spanning across several tech hubs in Europe and around the world.