Job Description
We are on the lookout for a Data Scientist - Customer Logistics, Choice to join the Logistics Team on our journey to always deliver amazing experiences.
In our Logistics Team, you’ll tackle high-impact challenges that make last-mile delivery efficient, affordable, and sustainable. Your work will directly improve experiences for riders, end customers, and merchants across the globe. Each enhancement you contribute will help Delivery Hero optimize delivery operations, supporting expansion into new areas like grocery and retail.
The Customer Logistics tribe’s mission is to build products that make it easy for local brands to run efficient operations and deliver a delightful order experience to customers so they order on repeat. The tribe comprises teams of skilled analysts, engineers, and scientists working together to deliver data solutions affecting every customer journey across all of Delivery Hero’s 70+ markets.
1. Drive the development and implementation of statistical, machine learning, and optimization models for choice optimization, rider fleet busyness and travel time prediction, and demand control. Collaborate with cross-functional teams to enhance the efficiency and performance of the machine learning models in across the vertical.
2. Analyse large-scale datasets to understand and identify opportunities by deploying sophisticated statistical techniques to improve decision-making in the domain.
3. Work on research initiatives to explore emerging trends and technologies in machine learning and data science, contributing to the advancement of Delivery Hero's digital products and algorithms. Stay informed about industry developments and incorporate new methodologies and best practices into our data science workflows.
Qualifications
4. You excel at modelling business problems using machine learning techniques covering feature engineering, model selection and design as well as evaluation and optimisation to deliver value to the business.
5. You have expertise in building and training advanced machine learning models with strong knowledge of the Python data toolkit ideally centring around Pandas, SQL, Sklearn, and PySpark.
6. Through the fluent use of SQL queries, you are able to explore our data universe and gather data to support your analysis and the development of machine-learning solutions.
7. You write clean, production-level code and effectively use software versioning with Git.
8. You are familiar with deploying and developing in cloud systems, ideally with experience in GCP and bigquery.
9. You love to learn and are a critical thinker and creative problem solver who strives for excellence; you are a team player who loves to collaborate and work with stakeholders from different tech teams in a diverse environment.
Nice to have:
10. Proven experience in addressing large-scale optimization problems (linear or mixed integer programming) is a strong asset.
11. Hands-on experience in creating causal models and deploying them in production is a plus.
12. Experience in designing and analysing advanced products/models experiments (switchback tests, quasi-experiments, non-standard A/B tests etc) is a plus.
13. Experience in working on logistics product development would be a great benefit.