Machine Learning Engineer - Dynamic Pricing and Multi-Armed Bandits (m/f/d)

As a Machine Learning Engineer specializing in Dynamic Pricing and Multi-Armed Bandits at SIXT in Lisbon, your primary responsibilities will include designing, implementing, and maintaining production-grade machine learning systems. You will work on advanced algorithms and collaborate with cross-functional teams to deploy your solutions. Continuous monitoring, analysis of model performance, and iterative improvement will also be crucial parts of your role.

To qualify for the Machine Learning Engineer position at SIXT, you should have a foundational understanding of machine learning or data science. While experience with reinforcement learning, multi-armed bandits, or dynamic pricing is a plus, it is not mandatory. Proficiency in Python and familiarity with machine learning frameworks such as TensorFlow or PyTorch are essential, along with a willingness to learn and adapt in a fast-paced environment.

A Machine Learning Engineer at SIXT should have strong technical skills, particularly in Python and major machine learning frameworks like TensorFlow or PyTorch. Additionally, experience with cloud platforms such as AWS, GCP, or Azure is beneficial. A production mindset focused on deploying and maintaining reliable and scalable ML models is also crucial for success in this role.

At SIXT, you can expect a flexible and enjoyable work environment, complete with a hybrid working model and no strict dress code. The company prioritizes work-life balance, offering 28 vacation days plus a day off for your birthday. You’ll also be part of a diverse, multinational team where collaboration and communication are highly valued.

SIXT offers various opportunities for professional development to Machine Learning Engineers, including participation in training programs and external conferences. You’ll have access to internal tech talks designed to foster both personal growth and technical expertise. This commitment to continuous learning ensures that you remain at the forefront of the machine learning field.

Reinforcement learning (RL) is a type of machine learning where an agent learns to make decisions by receiving rewards or penalties for its actions in an environment. In the context of dynamic pricing, RL can be applied to optimize pricing strategies by allowing the model to learn which prices yield the highest revenues based on historical data and customer behavior. When answering this question, demonstrate your understanding of RL concepts and how they can directly impact pricing decisions.

Multi-armed bandits are a framework for decision-making problems where an agent balances exploration (trying new actions) with exploitation (choosing the best-known actions). In pricing strategies, leveraging multi-armed bandit algorithms allows businesses to dynamically test different prices and promotions to optimize revenue. Highlight the significance of exploration vs. exploitation in your response and provide examples of when you might prefer one over the other.

When monitoring and evaluating machine learning models, it’s crucial to establish key performance indicators (KPIs) that align with business goals. Tools for visualization and analysis, such as dashboards, should be utilized to regularly track model performance. Discuss your experience with A/B testing, performance metrics like precision and recall, and how you would optimize models based on this data to showcase your ability to maintain models effectively.

In scenarios where inefficiencies are identified, it’s critical to analyze the process thoroughly to understand root causes. Share a specific example where you used data analysis to uncover inefficiencies, collaborated with stakeholders to design an improved process, and how you measured the outcomes of those changes. Demonstrating a data-driven approach will showcase your analytical skills in the role.

To keep a machine learning model relevant, I would ensure regular retraining using fresh data to capture changing trends or consumer behaviors. Establish a feedback loop with stakeholders to gain insights into model performance and identify the need for updates. Discuss leveraging CI/CD practices for ML to ensure the model's continuous deployment and monitoring, illustrating your proactive approach to model maintenance.

Communicating complex technical concepts to non-technical audiences is vital, particularly in cross-functional teams. Describe a specific instance where you successfully simplified a complex ML concept, using analogies or visual aids, ensuring that stakeholders could understand and leverage the information. This will demonstrate both your technical knowledge and communication skills, both key for the Machine Learning Engineer role at SIXT.

When discussing machine learning frameworks, mention your hands-on experience with popular tools such as TensorFlow, PyTorch, or other specialized libraries. Explain why you prefer one over the others, discussing aspects like ease of use, flexibility for experimentation, or available community support. Show enthusiasm for improving your skillset in these tools and your willingness to learn new frameworks if necessary.

Staying current in the fast-evolving field of machine learning is essential. Discuss specific strategies such as subscribing to leading journals, participating in forums like Kaggle, attending webinars or tech meetups, and following key figures in the industry on social media. Emphasize how you apply this knowledge to your work at SIXT, showcasing a commitment to continuous learning and adaptation.

Handling constructive criticism effectively is key for professional growth. Discuss how you approach feedback with an open mind, actively seeking clarification and recognition of blind spots in your projects. Share a specific example where you utilized feedback to improve your work or projects, exemplifying your willingness to adapt and learn from others' perspectives.

Collaboration is critical in machine learning projects, as insights from cross-functional team members can significantly enhance model performance and alignment with business strategies. Discuss examples where teamwork drove success—whether brainstorming, troubleshooting, or refining models. Also, highlight how effective communication plays a role in fostering collaboration within a diverse team at SIXT.