Senior Data Scientist - Dynamic Pricing M/F/X

Created on 01-08-2018

Location Berlin

CLOSED VACANCY Apply now

Description

The Challenge:
Our goal is to sell the right ticket at the right time to the right person for the right price to maximize revenue. This is an extremely formidable problem as the FlixBus network is huge and highly entangled. For instance, we serve ~250 000 trips through several thousand rides each day.
Airlines have faced this problem for decades, but their (rather old-fashioned) solutions are not directly applicable to the pricing structure, size and interconnectedness of the FlixBus network. Unlike a typical flight, a bus ride serves multiple trips (destination pairs), that have a shared resource: the bus capacity, i.e. number of seats. Furthermore, there are many more bus rides than flights within one day that serve the same or similar trips.

Why should you apply?
• Your work will revolutionize dynamic pricing and revenue management for large transportation networks
• Your work will have a major influence on company revenue, and hence you will be shaping the future of the FlixBus business
• You are free to employ the best suited technologies for the problem at hand, whether it's a cutting-edge deep learning algorithm or a stochastic optimization method from the 70s
• You will have access to a rich source of data that FlixBus has collected over the past years, including sales, search requests and competitor prices
• You will join a cross-functional team of highly motivated data scientists and engineers. We hold regular knowledge-sharing sessions for exchanging ideas about the latest technologies and organize bi-monthly HackrDays were we contribute to open source projects.
• You will be working with a modern data infrastructure based on docker, kubernetes and AWS
• We pay competitively, offer relocation support, and language course support

Your Tasks
• Conducting research and coordinating the R&D of the fellow data scientists in your team
• Supporting your product team in delivering business value – that is a team level responsibility. We call this responsibility Product First
• Analyzing large and complex data sets
• Bringing machine learning prototypes to production
• Working closely with multiple levels of stakeholders
• Driving the development of organizational-level topics that potentially require the collaboration of multiple teams spread across several domains
• Actively creating, collecting and spreading knowledge • Ideally you have a PhD/Advanced degree in Machine Learning/Mathematics/Statistics
• Proven track record as a highly skilled data scientist who is active in the data science community (e.g. open source contributions and publications in relevant journals)
• 5+ years industry experience in a similar role (data scientist, machine learning engineer, research scientist, revenue management engineer etc.)
• Advanced software development skills (preferably python), you know how to handle data from various sources and how to bring machine learning prototypes to production
• Deep understanding of machine learning algorithms, you know which one to choose for which problem
• Excellent communication skills
• Exceptional skills in one or more of the following: Operations research, econometrics, dynamic pricing, revenue management; Mathematical optimization, especially stochastic optimization; Statistics and probabilistic programming; Forecasting; Reinforcement learning and dynamic programming