Data Engineer

Location: Wrocław

Technologies we use

Required

• Python
• SQL
• Spark
• Polars

About the project

We are building the "brain" of the RTB bidder – a system that, on behalf of e-commerce clients, buys advertising space in real-time auctions. Our ML models decide which campaign to display, how the ad should look, and whether and for how much to bid.

We operate at scale: hundreds of thousands of requests per second, tens of billions of ML model decisions daily, and hundreds of millions of rows of auction logs hitting the database every day.

As a Data Engineer, you will develop processes that deliver data to these models. A key part of your work will be monitoring and verifying data quality and understanding its impact on model performance. You will also be responsible for optimizing processing and computation processes to efficiently handle the scale of our system.

This is how we organize our work

How we work

• within the organization
• you focus on one project
• you develop several projects simultaneously
• you focus on product development
• you focus on code maintenance

Your responsibilities

• Building and optimizing processes for feeding models with data.
• Designing and optimizing the data storage layer, including schemas and indexing for analytics and Real-Time systems performance.
• Creating an observability layer for input data, including dashboards and alerts to detect anomalies and drops in data quality feeding the models.
• Developing tools for monitoring production models, including detecting distribution shift.
• Implementing CI/CD practices supporting the creation, testing, and deployment of predictive models.

Our requirements

• Minimum 3 years of commercial experience in Data Engineering or a related data processing role.
• Very good knowledge of Python and SQL
• Experience in processing large data volumes using tools such as Spark and Polars
• Experience with analytical columnar databases
• Strong technical competencies: programming skills supported by an understanding of complex systems' operation
• Experience working in a data-intensive sector operating at scale
• Experience in designing and modeling data structures for advanced analytics and near real-time systems

Nice to have

• Knowledge of specific analytical engines: ClickHouse and/or StarRocks
• Knowledge of Kubernetes and GitOps tools (ArgoCD)
• Experience in the RTB (Real-Time Bidding) or programmatic advertising industry
• Experience in Machine Learning (ML) projects
• Knowledge of Go (Golang)

What we offer

• Working at a technological leader and partner of choice – we create content, services, and entertainment that accompany millions of Poles every day
• Free access to our products, such as Pilot WP or Audioteka – we want you to feel part of what we create ❤️
• Worksmile and a flexible benefits package – you choose what's important to you
• Access to free and anonymous psychological consultations
• Hybrid work option – we work 3 days in the office and 2 days from home, combining the flexibility of remote work with the best of the office
• Events that bring us closer – from seasonal campaigns (Children's Day is our favorite!) to webinars on health and neurodiversity
• Development opportunities through training within the WP Akademia program
• Chance for new challenges and directions within WP Holding companies – internal recruitment is within reach

How we work on the project

• Clean Code
• Continuous Deployment
• Continuous Integration

Benefits

• sports activities subsidy
• private medical care
• life insurance
• discounts on company products and services
• no dress code
• charitable initiatives

Wirtualna Polska Media S.A.

Wirtualna Polska Media S.A. – is the first-choice partner for Poles: we deliver engaging information, entertainment, and services, and inspire daily decisions. We operate in e-commerce, advertising, and media, coherently combining technologies.

All information regarding the processing of personal data in this recruitment can be found in the application form, after clicking the "Apply Now" button.