Senior Principal Applied Scientist - ZMS (all genders)

About the role

In this role, you will be responsible for driving the scientific vision and execution of bidding and allocation engines within Zalando Marketing Services. Your work will focus on optimizing algorithms to enhance platform health and user relevance while collaborating with cross-functional teams.

Success in this position involves advancing auction and mechanism design capabilities, ensuring a fair and efficient marketplace. You will also mentor senior team members and help foster a culture of technical excellence, making significant contributions to the scientific community.

The salary range for this position is between $140,000 and $210,000, reflecting the advanced expertise required.

Skills that matter here

• Machine Learning: You will apply machine learning techniques to optimize bidding algorithms.
• Optimization: The role involves deep expertise in optimization for complex systems.
• Control Theory: Control theory will be utilized in developing algorithms for effective budget pacing.
• Reinforcement Learning: You will implement reinforcement learning strategies in bidding optimization.
• Python: Strong proficiency in Python is required for architecting scalable data pipelines.

Who this role suits

• Candidates should have a strong academic background with a PhD in Machine Learning.
• You thrive in a collaborative environment and can translate complex problems into actionable solutions.
• A proven track record in Ad Tech or related fields is essential, along with experience in optimizing automated algorithms.
• Mentorship and leadership experience will help you succeed in guiding senior team members.

From the employer

Responsibilities

• Lead the research and development of our real-time bidding and allocation algorithms, optimizing for long-term platform health, advertiser performance, and user relevance.
• Advance our Auction and Mechanism Design capabilities to ensure a fair, efficient, and transparent marketplace.
• Collaborate with Product Managers, Engineers, and Analysts to translate complex business constraints into mathematical objective functions.
• Drive the long-term scientific and execution roadmap for ZMS Ad Tech Bidding Optimization in collaboration with Engineers and ML Scientists and foster a culture of technical excellence.
• Mentor and grow senior level members of the team, acting as a force multiplier for our scientific community.

Requirements

• PhD in Machine Learning with a track record of publications and industry experience.
• Proven track record of research excellence, evidenced by peer-reviewed publications in relevant fields such as Computational Advertising, Auction Theory, Mechanism Design, or Game Theory.
• At least 10+ years of experience in optimizing complex systems through automated algorithms, specifically within Ad Tech, Marketplaces, or related fields.
• Deep theoretical and technical expertise in optimization, control theory, or reinforcement learning applied to bidding and budget pacing.
• Expert knowledge of productionalizing ML models within ultra-low latency constraints and experience with large-scale distributed systems.
• Strong proficiency in Python and related stack, with a solid understanding of how to architect scalable data pipelines for sparse, high-dimensional advertising data.

Conditions

• 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.
• 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.