Data Scientist

Description

Job Summary: Responsible for developing, deploying, and transferring analytical models and pipelines to generate value for stakeholders. Key Highlights: 1. Building and deploying analytical products into production. 2. Experience in advanced modeling and analysis. 3. Mining industry experience and agile methodologies are valued. Job Objective Responsible for developing, deploying, and transferring analytical models and pipelines that support project objectives, ensuring value generation for stakeholders. Scope / Responsibilities * Consolidate project data, pipelines, and models. * Build, tune, and deploy analytical products into production. * Execute pilot projects and advanced analyses to validate developments and generate stakeholder value. * Document and execute the transfer of developments to operational continuity. Minimum Requirements (Mandatory) * Minimum 3 years of hands-on experience in advanced modeling and analysis. * Proficiency in Databricks, SQL, and Python. * Development of predictive models / Machine Learning (Neural Networks, Random Forest, anomaly detection, time series). * End\-to\-end solutions (data → model → consumption) and result visualization (Power BI, Plotly / Dash or equivalent). * Software engineering best practices and version control with Git (branches, pull requests, code review); work under agile methodologies (Azure DevOps). Mining Industry Experience (Highly Valued) * Demonstrable experience in the mining industry and its processes (Mine, Concentrator, Hydrometallurgy, Flotation, or associated processes) — highly valued by the client. * Ideally based on real operational process data from mining operations. Certifications (Desirable) * Databricks Machine Learning (Associate) or Azure Data Science / ML certifications. * Postgraduate education in Data Science or related fields. Project, People, and Communication Management * Time management: meets deadlines for models and analyses autonomously. * Requirements management: translates business needs into analytical solutions with support from the leader. * People / team management: coordinates effectively with process experts and the technical team. * Communication: clearly explains model results to end users and counterparts. Desirable Requirements (Differentiators) * MLOps practices: model versioning and registration (MLflow), reproducibility, and performance monitoring. * Material traceability; mine and plant operations. * Hydrometallurgy, leaching, or SX\-EW related processes. * Unity Catalog, Delta Lake, Databricks Asset Bundles (DAB), and PySpark. Academic Qualifications Professional degree in Engineering, Statistics, or a related field. Postgraduate education in Data Science is desirable.