Machine Learning Engineer – Allegro Pay

Allegro Pay is Central Europe’s largest and fastest-growing Fin Tech – the only place where financial solutions can be created at such a large scale, using state-of-the-art technology. We work on purchase financing and payment methods used daily by customers of Allegro, the most popular shopping platform in Poland and one of the largest e-commerce companies in Europe. We seek talented people who want to create powerful and robust solutions supporting a product with over a dozen million active users.

As a Machine Learning Engineer, you will be responsible for the machine learning / data platform in Allegro Pay and support Data Scientists in building machine learning models, making business-critical decisions, and enabling shipping to production while ensuring their high availability and performance.

• Developing a modern MLOps ecosystem aimed at automating the process of building and deploying machine learning models.
• Designing and implementing a modern platform for training predictive models (classifiers, deep neural networks, graph models).
• Deploying models to production and optimising deployment pipelines, to enable Data Scientists’ self-service.
• Managing, monitoring, and recalibrating models deployed to production.
• Supporting work on our Feature Store - an application providing predictors for models operating in production.
• Finding synergies and building connectors with Fin Tech AI platform, enabling agentic workflows to interact with our models and features.

Technologies you’ll encounter on the job: Python, Snowflake, Airflow, Azure, Kedro, MLFlow, .NET, Kubernetes, Tableau.

• We are an experienced team that is not afraid of hard problems and is constantly looking for development opportunities. We deploy our models at a scale found nowhere else in Poland.
• We approach the development of analytical solutions with an engineering mindset, drawing from methodologies originating in classical software development.
• You will be working on applications of ML in the finance sector, where the scale, sophistication of algorithms, impact on business, and technical requirements will be the key challenges.
• You will directly influence predictive models which change the way how millions of Allegro customers interact with the platform, in real-time.
• 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 will always support you.

• Graduated with a degree in Computer Science, Mathematics or another technical major.
• Have at least 2 years of experience in building ML-driven solutions.
• Fluently program in Python, know libraries from the MLE’s toolchain (scikit-learn, PyTorch, Pandas, FastAPI/Flask) and use development tools with ease.
• Are comfortable and efficient with AI assisted programming tools (Opencode, Codex, Claude).
• Have some experience with modern Python-based orchestration tools (Airflow, Dagster).
• Have good analytical skills and know SQL.
• Know and apply the Dev Ops principles in their work.
• Understand statistical and machine learning methods, especially algorithms based on decision trees and neural networks, on a practical level.
• Are able to make independent decisions within the scope of their responsibilities and take ownership of the code they created.

• Experience with the .NET ecosystem.
• Knowledge of cloud-based MLOps tools (AzureML, Google Vertex AI, AWS Sagemaker).
• Experience with modern SQL-based data transformation frameworks - dbt.

• Flexible working hours in the hybrid model (4/1) - working hours start between 7:00 a.m. and 10:00 a.m. We also have 30 days of occasional remote work.
• Annual bonus based on your annual performance and company results (up to 10% of the gross annual salary depending on your end-year assessment).
• Well-located offices (with e.g. fully equipped kitchens, bicycle parking, terraces full of greenery) and excellent work tools (e.g., raised desks, ergonomic chairs, interactive…