Working at Sky Italy in Data Platform & Analytics (DP&A) is a unique opportunity to design and implement the best solutions to exploit the power of data in combination with our platform capabilities by working on advanced analytics use cases to derive knowledge and gain insights on how to keep our customers experience at top level.

Role overview

The candidate will be a key person for advanced analytics usage within DP&A by promoting Machine Learning (ML) approaches and maintaining/improving the current Artificial Intelligence (AI) end to end infrastructure with the aim to maximize the values of data and push toward the evolution of new use cases thanks to the adoption of the Big Data ecosystem.

Main activities:

• Design ML systems to automate models training, prediction and performance validation
• Working on prototypes, experiment new approaches and test several solutions on ML algorithms and tools application
• Industrialize end to end solutions by defining and applying best practices in ML Ops field
• Analyze huge volumes of historical data to make predictions and trends forecasting
• Maximize the value of available data by proposing new potential use cases on top of heterogeneous datasets, raw data and complex models with the application of descriptive, predictive and prescriptive analysis techniques

Responsabilities:

• Research and implement appropriate ML algorithms and tools, design ML systems, propose AI applications according to requirements and data science prototypes
• Select appropriate datasets, design efficient data models and data representation methods
• Understanding business objectives and propose/developing models that help to achieve them, along with metrics to track their progress
• Managing available resources such as hardware, data, and team staffing so that project deadlines are met
• Design and deploy to production end to end ML pipelines by using best practices for monitoring/retraining/redeploying
• Analyzing/ranking ML algorithms that could be used to solve a given problem and perform statistical analysis and fine-tuning according to test results
• Define the preprocessing or feature engineering to be done on a given dataset, analyze models underperformance and design strategies to overcome them

Skills required:

• Proficiency with ML frameworks, libraries, data structures, data modeling, and software architecture
• Knowledge of Cloud environments with experience on GCP Platform Cloud-based solutions (e.g. BigQuery, Cloud Pub/Sub, AI Platform, GCS, Cloud Functions)
• Advanced proficiency with Python code writing and basic libraries for ML and data science (e.g. NumPy, Pandas, Scikit-learn, TensorFlow)
• Expertise in visualizing and manipulating big datasets
• Knowledge of SQL/NoSQL language/DB: querying, modeling and data structures
• Knowledge of maintenance and ongoing development of continuous build/integration infrastructure
• Excellent analytical and problem-solving abilities with in-depth knowledge of mathematics and statistics
• At least two years’ experience as a ML engineer and Proficiency with English language
• Master's degree in computer science, data science, mathematics, or a related field.