.Machine Learning Engineer - Reinforcement Multi-Armed Bandits (m/f/d)Full-timeLegal Entity: Sixt Research Development Services, Lda.Join our team of data science and machine learning experts to shape the next generation of intelligent pricing strategies.
Our mission is to apply cutting-edge techniques—including reinforcement learning, multi-armed bandits, and Bayesian inference—to optimize dynamic pricing decisions.
We build scalable models and systems that directly impact millions of customers, enabling more efficient revenue management processes and a superior user experience.YOUR ROLE AT SIXT:Develop and Enhance ML Solutions: Design, implement, and maintain production-grade machine learning systems, with a strong focus on bandit algorithms and reinforcement learning methods for dynamic pricing.Cross-Functional Collaboration: Work closely with teams in data science, engineering, product management, and business operations to bring experimental models into a robust production environment.Monitoring and Analysis: Continuously track model performance, visualize key metrics, and conduct deep-dive analyses to understand changes in system behavior and their impact on business outcomes.Iterative Improvement: Collaborate with business stakeholders to identify inefficiencies in current processes and propose data-driven, ML-powered solutions to address them.Knowledge Sharing: Communicate results, methodologies, and technical insights to audiences of varying technical backgrounds, ensuring that both business and technical teams understand the value of your work.YOUR SKILLS MATTER:Foundational Experience in ML: Some background in machine learning or data science.
Prior exposure to reinforcement learning, multi-armed bandits, Bayesian methods, or dynamic pricing is a plus, but not required.Technical Skills: Proficiency in Python and familiarity with modern ML frameworks (e.G., TensorFlow, PyTorch).
Experience with cloud platforms (AWS, GCP, or Azure) is beneficial.Production Mindset: Comfortable deploying and maintaining ML models in a production environment, ensuring reliability, scalability, and adaptability.Growth-Oriented: Passionate about learning new methods and solving real-world problems.
Even if you don't have all the experience listed, we encourage you to apply if you're excited about bandit algorithms, dynamic pricing, and advanced ML techniques.Communication & Teamwork: Fluent in English and enthusiastic about working within a diverse, multinational team.WHAT WE OFFER:Generous Time Off: Enjoy 28 days of vacation, an additional day off for your birthday, and 1 volunteer day per year.Work-Life Balance & Flexibility: Benefit from a hybrid working model, flexible working hours, and no dress code.Great Employee Benefits: Access discounts on SIXT rent, share, ride, and SIXT+, along with partner discounts