Senior Specialist Data Science

Description:

Industry: Steel/ Metal

Location: Vanderbijlpark, Johannesburg

Salary: Market- related

Introduction

The company is seeking a skilled Data Science Senior Specialist. Key responsibilities include developing and implementing machine learning models for manufacturing operations, collaborating with engineering and operations teams, integrating solutions into workflows, and analysing complex datasets. The candidate should be an effective communicator, collaborative, results-oriented, and adaptable.

Minimum Requirements

Qualifications

• B Degree (NQF7) in Engineering, Data Science, Computer Science, or a related field.

• Machine Learning or Business Intelligence-related certifications will be advantageous.

• A postgraduate qualification would be an advantage.

Experience

• Minimum 8 years’ relevant experience in data science, preferably in a manufacturing or operational environment.

• Strong hands-on experience with supervised learning techniques such as linear and logistic regression, decision trees, random forests, support vector machines, and gradient boosting methods (e.g., XGBoost, LightGBM).

• Demonstrated expertise in applying supervised models for classification, regression, and prediction of key operational metrics (e.g., quality, downtime, yield).

• Practical experience with unsupervised learning techniques such as k-means clustering, DBSCAN, hierarchical clustering, and dimensionality reduction methods like PCA and t-SNE.

• Applied unsupervised methods for root cause analysis, anomaly detection, sensor signal pattern recognition, and process behavior segmentation.

• Proficient in Python and its machine learning ecosystem, including pandas, NumPy, scikit-learn, matplotlib/seaborn, and preferably TensorFlow or PyTorch.

• Hands-on experience using Azure Databricks for developing, training, and scaling machine learning models, including data pipeline creation, notebook development, and distributed processing.

• Exposure to MLOps practices, including model versioning, monitoring, CI/CD pipelines, and automation of retraining using tools like MLflow, Azure Machine Learning, and Git-based workflows.

• Demonstrated capability in handling large datasets and data from diverse sources (e.g., PLCs, MES, ERP).

• Experience in deploying, monitoring, and maintaining models in production environments.

• Experience with Business Intelligence tools (e.g., Power BI) is beneficial.

Personal Attributes

• Strong analytical thinking and problem-solving capabilities.

• Ability to apply data science to real-world manufacturing challenges.

• Effective communicator with the ability to explain technical concepts to non-technical stakeholders.

• Collaborative and capable of working in cross-functional teams.

• Results-oriented with a strong sense of accountability and initiative.

• High attention to detail and strong organizational skills.

• Adaptable, self-driven, and committed to continuous learning.

• Ability to work independently and manage multiple priorities.

Job Description

Key Performance Areas

• Develop and implement predictive and prescriptive machine learning models for manufacturing operations.

• Collaborate with engineering and operations teams to identify opportunities for data-driven improvements.

• Integrate machine learning solutions into operational workflows to drive efficiency, quality, and reliability.

• Design scalable and reusable data science solutions in line with best practices.

• Analyse complex manufacturing datasets to uncover trends, anomalies, and opportunities.

• Support the business with clear, data-backed insights and strategic recommendations.

• Maintain and monitor performance of deployed models to ensure long-term effectiveness.

• Promote a data-driven culture through knowledge sharing and collaboration.

Requirements:

• B Degree (NQF7) in Engineering, Data Science, Computer Science, or a related field.

• Machine Learning or Business Intelligence-related certifications will be advantageous.

• A postgraduate qualification would be an advantage.

• Minimum 8 years’ relevant experience in data science, preferably in a manufacturing or operational environment.

• Strong hands-on experience with supervised learning techniques such as linear and logistic regression, decision trees, random forests, support vector machines, and gradient boosting methods (e.g., XGBoost, LightGBM).

• Demonstrated expertise in applying supervised models for classification, regression, and prediction of key operational metrics (e.g., quality, downtime, yield).

• Practical experience with unsupervised learning techniques such as k-means clustering, DBSCAN, hierarchical clustering, and dimensionality reduction methods like PCA and t-SNE.

• Applied unsupervised methods for root cause analysis, anomaly detection, sensor signal pattern recognition, and process behavior segmentation.

• Proficient in Python and its machine learning ecosystem, including pandas, NumPy, scikit-learn, matplotlib/seaborn, and preferably TensorFlow or PyTorch.

• Hands-on experience using Azure Databricks for developing, training, and scaling machine learning models, including data pipeline creation, notebook development, and distributed processing.

• Exposure to MLOps practices, including model versioning, monitoring, CI/CD pipelines, and automation of retraining using tools like MLflow, Azure Machine Learning, and Git-based workflows.

• Demonstrated capability in handling large datasets and data from diverse sources (e.g., PLCs, MES, ERP).

• Experience in deploying, monitoring, and maintaining models in production environments.

• Experience with Business Intelligence tools (e.g., Power BI) is beneficial.

• Strong analytical thinking and problem-solving capabilities.

• Ability to apply data science to real-world manufacturing challenges.

• Effective communicator with the ability to explain technical concepts to non-technical stakeholders.

• Collaborative and capable of working in cross-functional teams.

• Results-oriented with a strong sense of accountability and initiative.

• High attention to detail and strong organizational skills.

• Adaptable, self-driven, and committed to continuous learning.

• Ability to work independently and manage multiple priorities.

• Develop and implement predictive and prescriptive machine learning models for manufacturing operations.

• Collaborate with engineering and operations teams to identify opportunities for data-driven improvements.

• Integrate machine learning solutions into operational workflows to drive efficiency, quality, and reliability.

• Design scalable and reusable data science solutions in line with best practices.

• Analyse complex manufacturing datasets to uncover trends, anomalies, and opportunities.

• Support the business with clear, data-backed insights and strategic recommendations.

• Maintain and monitor performance of deployed models to ensure long-term effectiveness.

• Promote a data-driven culture through knowledge sharing and collaboration.