Data Scientist

Description:

Key Responsibilities:

Enterprise Data Integration – Consolidating data across the enterprise into a single source of truth through modern data warehousing and lakehouse architectures.
Business Intelligence Enablement – Developing and maintaining enterprise-level analytics to support the monitoring and optimization of key business functions such as Finance, Supply Chain, Customer Service, Project Management, and Engineering.
Applied Machine Learning for Equipment Monitoring – Designing and deploying machine learning models within web applications to enable predictive maintenance, anomaly detection, failure prediction, and estimation of the remaining useful life (RUL) of spare parts.
Stakeholder Engagement and Ad Hoc Analytics – Collaborating with internal and external stakeholders to address data-driven inquiries and support project-specific analysis related to equipment performance and operational efficiency.
Insight Communication and Data Storytelling – Delivering presentations and effectively communicating analytical insights to a wide range of stakeholders, ensuring that data-driven strategies are clearly understood and actionable.

Requirements:

Technical Skills

Data Engineering & Integration
Proficiency with Microsoft Fabric (OneLake, Lakehouse, Data Warehouse) - advantageous
Experience with ETL/ELT pipeline development (e.g., Azure Data Factory, Synapse Pipelines)
Strong knowledge of Kimball dimensional modeling (star vs. snowflake schema)
SQL (T-SQL, M code)
Data ingestion from various sources (ERP, On-prem and Cloud databases, CRM, SharePoint, OneDrive, etc.)
Knowledge of Data Gateways for on-prem data and cloud resources integration.
Knowledge of Databases (PostgreSQL, SQL Server)

Technical Skills
Data Engineering & Integration

Proficiency with Microsoft Fabric (OneLake, Lakehouse, Data Warehouse) - advantageous
Experience with ETL/ELT pipeline development (e.g., Azure Data Factory, Synapse Pipelines)Strong knowledge of Kimball dimensional modeling (star vs. snowflake schema)
SQL (T-SQL, M code)
Data ingestion from various sources (ERP, On-prem and Cloud databases, CRM, SharePoint, OneDrive, etc.)
Knowledge of Data Gateways for on-prem data and cloud resources integration.
Knowledge of Databases (PostgreSQL, SQL Server)

Machine Learning & Advanced Analytics

Python (primary), R (optional), Spark (beneficial)
Time series forecasting (e.g., ARIMA, Prophet, LSTM, etc.) -
Descriptive and Inferential Statistics
Predictive Maintenance Modelling: failure prediction, anomaly detection, RUL estimation
ML frameworks such as Scikit-learn
Model Deployment using Azure Machine Learning, Azure Functions, or AKS

Business Intelligence

Strong skills in Power BI (Data Modelling, M Code, DAX, dashboards)
Experience answering ad hoc queries and interpreting complex datasets
Ability to perform root cause analysis and correlation studies on equipment performance

Software & Cloud Development – Advantageous

Familiarity with REST APIs and microservices for integrating ML models into web applications.
Understanding of web app deployment and hosting on Azure App Services

Supply Chain & Inventory Analytics – Advantageous

Understanding of inventory control, demand planning, working capital optimization
Experience with inventory optimization models (e.g., EOQ, reorder point models, ABC analysis)


Qualification:

Degree in Computer Science, Engineering or related field

Experience:

1-3 years + experience within a data science environment, preferably with mining and mineral processing experience or supply chain experience