Senior Software Engineer - Machine Learning

The Lounge Assortment Optimisation team builds the decision products behind a better assortment and customer experience. Our portfolio combines:

• Optimisation systems that improve how the assortment is planned and operated;
• Forecasting products that estimate demand, sell-through, and commercial outcomes; and
• Generative AI solutions that improve product curation, content creation, and operational workflows.

As a Senior Software Engineer (Machine Learning), you will make these products reliable in production. You will build the data, software, deployment, and monitoring foundations that allow models to move safely from experimentation into daily commercial use.

This is an engineering role at the intersection of data platforms, machine learning, optimisation, and product development. You will work closely with Applied Scientists, Product Managers, Engineers, and commercial stakeholders to turn ambiguous problems into trusted, scalable systems.

At Zalando, our vision is to be the leading pan-European ecosystem for fashion and lifestyle e-commerce - one that is inclusive by design. We only assess candidates based on qualifications, merit, and business needs. We welcome applications from people of all gender identities, sexual orientations, personal expressions, racial identities, ethnicities, religious beliefs, and disability statuses. We only want to know why you’re great for this role, so please avoid including your picture, age, and marital status in your CV as well.
We want to provide you with a great candidate experience. Please feel free to inform us of any accommodations you may need, so we can best support and assist you throughout the hiring process.
do.

BETTER - our diversity & inclusion strategy:

• Build and operate production systems for optimisation, forecasting, machine learning, and Generative AI use cases.
• Design scalable data and ML pipelines using Python, Databricks, Spark, Airflow, and dbt, with clear data contracts and reliable failure handling.
• Enable Applied scientists to develop and evaluate models efficiently by providing reusable training, evaluation, deployment, and experiment‑tracking capabilities.
• Product ionise models: define dependable inputs and outputs, automate deployment, monitor quality and performance, and make model behaviour traceable in production.
• Develop and operate workloads in the appropriate execution environment:
  Databricks jobs for distributed data and ML processing, and Dockerised applications running as Kubernetes pods where that runtime is needed.
• Build operational dashboards, alerts, and runbooks so that users and engineers can understand system state, identify issues, and respond effectively.
• Work with product and commercial partners to convert business rules and decision requirements into maintainable software components.
• Raise the engineering bar through pragmatic standards for system design, testing, code review, CI/CD, observability, and operational ownership.
• You have 3+ years of experience building and running data or ML systems in production, for example in MLOps, data engineering, ML platforms, or ML product development.
• You write maintainable production Python and follow established software‑delivery practices, including automated testing, code review, and CI/CD.
• You're strong in software engineering fundamentals: reliability, scalability, observability, and maintainable system design.
• You understand how cloud workloads are deployed and run, including AWS, Docker containers, and Kubernetes‑based execution.
• You communicate clearly with both technical and non‑technical stakeholders and enjoy turning ambiguous problems into dependable systems.
• Experience with Generative AI products, including LLM…