Senior Machine Learning Engineer (all genders) at zalando – Berlin | Jobyssey

THE ROLE & THE TEAM

Zalando Marketing Services (ZMS) stands for a new era of marketing in fashion e-commerce. We enable fashion, beauty, and lifestyle partners to engage with +60 million active customers across European markets on Zalando and beyond, providing access to exclusive audiences and smart marketing tools. We are ambitious and committed to being the starting point of fashion for our customers and partners; therefore, we are re-founding and scaling our Applied Science and Engineering backbone for Ads Personalization, working backwards from user, content, and context understanding.
In ZMS Tech, we are currently evolving our real-time inference sponsored prediction system and building a brand-new Ad candidate retrieval system to deal with millions of sponsored ads opportunities in a real-time, low-latency, and high-volume fashion. As a Senior ML/Data Engineer, you will work with a talented cross-functional team made up of Applied Scientists, Software Engineers, Data Engineers, Product Managers, and Designers. Together, you will build and scale data pipelines and machine learning infrastructure for our next-generation AdTech platform.

INCLUSIVE BY DESIGN
If you think you have what it takes, we encourage you to apply even if you don't meet every single requirement. You may just be the right candidate for this or other roles!
At Zalando, our vision is to be the leading pan-European ecosystem for fashion and lifestyle e-commerce – one that thrives on diversity and is truly inclusive by design. We believe that diverse teams fuel innovation and creativity, and we actively seek out talent from all backgrounds.
We actively seek to reduce bias in our hiring and employment processes, focusing on your qualifications, skills, and contributions. To support this, we kindly ask that you refrain from including personal details such as your photo, age, or marital status in your CV, ensuring a fair and equitable evaluation based solely on your abilities and potential.

We are committed to providing an exceptional and accessible candidate experience for everyone. If you require any accommodations to support you throughout the hiring process, please let us know – we are here to assist you.

Discover more about our commitment to creating a diverse and inclusive workplace:

WHAT WE’D LOVE YOU TO DO (AND LOVE DOING)

Design & Architecture: Play a key role in the design, architecture, and development of end-to-end data engineering and MLOps solutions with full operational responsibilities on cloud infrastructure (AWS, Databricks, Kubernetes).
Streaming Pipelines: Gather requirements and design high-throughput, low-latency batch and real-time feature pipelines using Apache Flink (Java) and Spark (Python) to provision production-grade features to our central Hopsworks Feature Store.
System Operationalization: Drive the operationalization, model serving, and maintenance (MLOps/MLaaS) of our real-time inference sponsored prediction system and new Ad candidate retrieval systems.
Science Collaboration: Collaborate closely with Applied Scientists to optimize data pipeline runtime, data quality, and model performance, latency, and memory usage.
Operational Excellence: Take ownership of the operational excellence of our AI systems, implementing robust CI/CD pipelines, continuous monitoring, and automated alerting for distributed systems to maximize scalability and reliability.
Communication & Roadmapping: Communicate effectively with product managers, data scientists, and engineering peers, translating complex engineering concepts into actionable roadmaps.
Workflow Automation: Strive to continuously improve and automate the time-to-market for the team's experimentation-to-production workflows.

WE’D LOVE TO MEET YOU IF

Solid Foundation: You hold a degree in Computer Science, a related technical field, or have equivalent practical experience showcasing strong software engineering fundamentals.
Streaming & Data Engineering: You have significant hands-on experience designing, building, and maintaining high-throughput, low-latency data streaming applications. Practical experience with Apache Flink and Spark is highly required.
MLOps & Model Serving: You possess professional experience in machine learning operationalization, model serving (e.g., Triton, SageMaker), data version control, and workflow orchestration (e.g., Airflow or Databricks workflows).
Strong Programming Skills: You are proficient in Java and/or Python, with a strong passion for writing clean, testable, and maintainable production code. Familiarity with ML libraries (e.g., PyTorch, TensorFlow) is a major plus.
Modern Practices: You are well-versed in Agile methodologies, CI/CD pipelines, and establishing effective metrics and monitoring for large-scale distributed systems.
Collaboration & Mentorship: You have experience working closely with applied scientists and mentoring other engineers, with excellent verbal and written communication skills to bridge technical gaps across stakeholders.

OUR OFFER
Zalando provides a range of benefits, here’s an overview of what you can expect. Ask your Talent Acquisition Partner to learn more about what we offer.

27 days of holiday a year to start for full-time employees (+1 day for every calendar year up to 30 days)
2 paid volunteering days a year
Hybrid working model with up to 60% remote per week, actual practice is up to each team to best support their collaboration
Work from abroad for up to 30 working days a year
Employee shares program
40% off fashion and beauty products sold and shipped by Zalando, 30% off Lounge by Zalando, discounts from external partners
Relocation assistance available (subject to prior agreement)
Family services, including counseling and support
Health and wellbeing options (including Wellhub, formerly Gympass)
Mental health support and coaching available
Drive your development through our training platform and biannual peer-to-peer review

Explore more jobs