Senior Data Scientist - Store Operations (all genders)

Key Skills

Java Programming, Management, Python Programming, Database, SQL, AWS, Big Data Technology, Apache Hadoop, Machine learning techniques, Google BigQuery, Dataproc, NoSQL, Apache Hive, Apache Airflow, Kubernetes-K8s, Continuous Integration & Continuous Delivery - CI/CD, Google Cloud Platform (GCP), SPARK Programming

Job Description

We are looking for (Senior) Data Scientist to join our Operation tribe in the Quick Commerce vertical.

Quick Commerce comprises varied teams of deep technical and data expertise for developing the next generation of E-Commerce quick-delivery services. As a part of the Operations tribe, we’re developing global solutions across store management, order fulfillment, supply chain, and demand planning in order to optimize operational processes. We’re reinventing online shopping and building a scalable product ecosystem to enable cost and time effective operational processes.

As a part of the Store Operations, we leverage the power of data science to build machine learning and mixed-integer programming solutions for our next-generation platform, which works on expanding our amazing delivery to new products such as groceries, pharmaceuticals, flowers, and more. We focus on very interesting and challenging problems related to location-based inventory layouts and workforce staffing & route optimization in warehouses across the globe while improving customer experience.

If you're a creative problem solver who is eager to solve technical challenges to deliver your solutions to customers around the globe, and hungry for a new adventure, an international workplace is waiting for you in the heart of Berlin!

Join our Operations tribe now and become a Delivery Hero!

Your mission:

• You drive building and improving existing machine learning methodologies by developing data sources, testing model enhancements, fine-tuning model parameters, and running computational experiments. You analyze large amounts of data from different services of our system, and their associated business functions.
• You formalize assumptions about how models are expected to behave, creating definitions of outliers, developing methods to systematically identify these outliers, and explaining why they are reasonable or identifying fixes for them.
• Apart from writing code for analyzing data and building statistical and machine learning models, you demonstrate software development engineering skills that you can use for designing computationally effective machine learning operationalization (MLOps/ MLaaS) in large-scale production environments on AWS/ GCP.
• You work in synergy with our data scientists, engineers, partners, and product managers, to facilitate the execution of evaluation experiments at scale, and drive practically applicable designs of machine learning models in production.
• You communicate with business customers verbally and in-writing on various levels of technical knowledge, educating them about our research, as well as sharing insights and recommendations
• You work in a goal-driven environment.

Your heroic skills:

• Master’s or PhD degree in a quantitative field such as Machine Learning (ML), Data Science, Statistics, Applied Mathematics, Physics, Computer Science, or Economics or 4 years of experience in the field. 
• Leadership and/or mentorship abilities in a data science and engineering environment to drive operational excellence and best practices.
• Fluency in Python and other scripting and/or computing languages (e.g. R, Scala, C++, Java).
• Deep knowledge of ML lifecycle, statistical methodologies, A/B testing, practical usage of ML libraries and scientific stack (e.g. scikit, matplotlib, xgboost, etc.).
• 4+ years of relevant working experience in an analytical role involving data extraction, analysis, data querying languages (e.g. SQL, NoSQL, Hadoop/Hive), and statistical modeling.
• Experience in processing, filtering, and presenting large quantities (Millions to Billions of rows) of data from different product groups and business functions.
• 5+ years of professional experience, at-least 3 of them in developing machine learning solutions, and shipping in a large-scale production environment.
• You care about agile software processes, data-driven development, reliability, and disciplined experimentation.
• Ability to effectively articulate technical challenges and solutions, and deal well with ambiguous/ undefined problems; ability to think abstractly.
• Strong verbal and written communication skills with fluency in english 

Nice to have

• Experience with time series modeling, operations research or machine learning forecasting.
• Experience in developing data-driven solutions to address problems related to supply chain and store operations.
• Experience with NoSQL databases and big data technologies such as Spark, BigQuery, dataProc, Hadoop/Hive.
• Familiarity with common CI/CD tools like Jenkins, and experience with running code in a container or modern infrastructure environments like Kubernetes.
• Experience with designing scalable ML pipeline architecture on GCP/ AWS, orchestrating with workflow management tools such as Apache Airflow, or leveraging ML tools such as mlflow, sagemaker, vertex-ai.