Principal Specialist, Data Science & Analytics

Job Purpose

The Lead Specialist, Data Science & Analytics, acts as a technical leader and senior practitioner, driving development, deployment, and scaling of machine learning, AI, and advanced analytics solutions across Maaden. The role ensures analytics products are designed, validated, industrialised, governed, and adopted at scale, providing measurable value across mining, processing, operations and enterprise functions. This specialist analyzes data, extracts insights, and builds predictive models that help organisations make smarter decisions and solve difficult problems.

• Lead end‑to‑end data‑science delivery
• Develop, implement and maintain databases and data‑collection systems
• Own the full lifecycle of ML/AI initiatives – from problem framing, data exploration, feature engineering, model development, validation, to MLOps handover
• Deliver scalable and production‑grade models, ensuring alignment with enterprise data governance and AI standards
• Perform statistical analysis to understand and interpret data insights
• Apply data‑mining techniques to identify patterns, trends and relationships in large datasets
• Build predictive models and machine‑learning algorithms to forecast future outcomes
• Create clear visualisations and reports to communicate findings to stakeholders
• Work with cross‑functional teams to understand business needs and provide data‑driven solutions
• Design and maintain reliable data pipelines and models in partnership with data engineering for accurate, timely, and trustworthy data
• Ensure data security and compliance with relevant regulations
• Drive experimentation, model versioning, automated retraining, and continuous improvement
• Translate business needs into AI/analytics solutions
• Establish frameworks and operating models that make data science accessible, scalable and embedded within business and technical functions
• Engage stakeholders to identify value‑creation opportunities and convert them into actionable analytics use cases
• Build value hypotheses, KPIs, success criteria and solution roadmaps in collaboration with data & AI leadership and business teams
• Industrialise AI/ML models (ML‑Ops & Architecture)
• Partner with data engineering, data platforms and cloud/OT architecture teams to embed models into enterprise systems and operational layers
• Set standards for deployment, testing, monitoring, drift handling and lifecycle governance
• Integrate predictive and optimisation models into enterprise platforms, control systems and digital twins
• Leverage ML, optimisation and computer vision to improve performance, reliability and sustainability
• Ensure compliance with Maaden’s Responsible AI, data quality and governance frameworks
• Promote reproducibility, documentation, lineage tracking and auditability of all data‑science assets
• Communicate insights, risks and recommendations to decision‑makers using compelling narratives and visualisation
• Track value realisation, adoption metrics and operational impact to guarantee measurable benefit

• Bachelor’s degree in Computer Science, Data Science, Engineering, Mathematics, Statistics or related fields

• Data Engineering (IT + OT)
• Experience designing and maintaining data pipelines across IT and OT environments
• Exposure to sensor data, streaming / real‑time data processing and industrial data sources
• Ability to collaborate with data engineering teams to ensure reliable, timely, trusted data flows
• MLOps / Agent Ops
  • Experience in model deployment and lifecycle management, including:
  • Transition from model development to production and scale
  • Monitoring, retraining, versioning, and drift management
• Familiarity with automation and operationalization of ML/AI workloads
• Cloud & Analytics Platforms
  • Experience working with enterprise cloud platforms, preferably:
  • Microsoft Azure Data Platform
  • Databricks AI Platform
  • Microsoft AI Foundry / Microsoft AI Factory
• Understanding of cloud‑native architectures for scalable analytics and AI solutions

• Model accuracy & reliability: performance, drift stability, and operational uptime
• Adoption & business impact: value realised, user adoption, integration success
• Delivery velocity: timeliness of development cycles and deployment readiness
• Compliance & quality: compliance with responsible AI, governance, and documentation standards