GUCCI Digital Data Scientist
Gucci - Regular
MILANO - Italy
She/he will be carrying on the following activities:
- Build robust and efficient production data pipelines, ETL and EL workflows and optimize current ones, to assure continuous delivery of accurate and quality KPIs to end users.
- Prototype, develop and operationalize ML models to improve Customer Experience and Conversion Probability, working with Product Development teams.
- Generate insights using multiple data sources from our on-premises and cloud IT, create compelling stories using Powerpoint and Jupyter Notebooks, support Business leadership with ad hoc analysis.
- Design, deploy and maintain scalable dashboards for the top management and other internal/external stakeholders, with a focus on the backend data infrastructure.
- Improve and optimize current web KPIs and alert-systems using automation techniques and machine learning, write programming code ready to be integrated in production, contribute to the creation and improvement of new data sources.
- Be a pivotal player involved in all the data science projects across the organization, working with PMs, Engineers and Analysts from different departments both at Gucci and Kering level.
- Be a Data Science evangelist, spreading analytics culture at different levels, from code readability and documentation, to storytelling and knowledge sharing.
- At least 3 years of experience in Data Scientist / Data Engineering roles, in fast paced environments.
- Programming proficiency in Python and data analysis modules : Pandas, NumPy, SciPy, StatsModels and Scikit-Learn.
- Good knowledge of SQL/DML with a focus on scalability, building fast and efficient queries or data structures (indexing, clustering and partitioning).
- Data engineering skills, ETL, EL, data pipelines (batch and stream jobs) and relative technologies.
- Cloud computing, mainly GCP. Experience on AWS appreciated.
- Knowledge of Data visualization tools such as Data Studio and Tableau.
- Experience with web APIs.
- Experience in operationalization of Machine Learning models and virtualization frameworks such as Docker.
- Ability to create and manage cross functional relationships.
- Positive, enthusiastic, able to take initiative with a geek-can-do attitude.
- Proficient in English (both written and spoken).
- Previous experience in a Data science consultancy team, or Digital Marketing units is a big plus.
- Knowledge of one or more of the following Apache frameworks: Airflow, Beam, Spark.
- Experience with Google Cloud Platform Services: GCS, Pub/Sub, Cloud Functions, Composer, Data Flow and Big Query.
- Experience in one or more of the following tools: Google Tag Manager, Google Cloud Platform, Firebase, G4, MicroStrategy.
- Expertise with Machine Learning supervised (linear, non-linear regression, ensemble decision trees, gradient descent boosting) and unsupervised models (K-means clustering).
- Knowledge of other Machine Learning/AI fields (neural networks, natural language processing, association rules etc..).
- Full time