Senior Data Scientist (Processing)

Gauteng, Full Time

Accountability:
Understanding vast amounts of data can reveal hidden patterns and insights crucial for efficiency and innovation. The role is designed to harness the power of data, converting raw numbers into actionable strategies. This position will delve deep into the mining data, analysing geological information, operational efficiency, and predictive maintenance, ensuring that Glencore stays ahead in a data-driven decision making.
Copper business plan recognizes that the future of mining hinges on smart data utilization and data driven decision making. The role is instrumental in translating data into tangible business value. Whether it’s optimizing extraction processes, predicting asset maintenance, or assessing ore quality using machine learning algorithms, the outputs produced by this role directly align with and empower the company’s strategic objectives. 
Acts as a bridge between mining experts and the wealth of data the mining operation produces. By introducing advanced analytical techniques, predictive modelling, and AI-driven insights, the role elevates OE team member’s capacity to make informed decisions and models.
Key Relationships

Global Lead Data Scientist
Data Scientist, Business Analysts, Technology Project Managers
Regional Operational Excellence and Technology Transformation Manager
Lead Data Engineer
Regional Leads of Automation
Operational Excellence Managers
PMO Lead
Planning and Cost Engineer
Project Managers
Project Services Team

Qualifications & Skill Requirements:

Degree in Engineering, Computer Science, or a related business discipline
Desirable Master’s or PhD in Statistics, Mathematics, Computer Science, or another quantitative field.
Agile Certification desirable
Lean Six Sigma Certification desirable
Project Management Certification desirable

Competencies:

 Ensures Accountability
 Develops Talent
 Drives Engagement
 Instils Trust
 Collaborates
 Customer Focus
 Plans and Aligns
 Strategic mindset
 Communicates effectively.
 Decision Quality
 Courage
 Being Resilient

 
Work Experience:
Qualifications and Experience (min 3 of the 4 points):

More than 10 years of work experience
More than 5 years of experience manipulating data sets and building statistical models.
More than 1 year of experience on site mines, in operations or dispatch.
Leadership experience, technically guiding and motivating data scientists and analysts.
Data Science and Machine Learning Skills:
Solid understanding of data science and machine learning foundations.
Knowledge of a variety of machine learning techniques and their advantages/drawbacks.
Knowledge of advanced statistical techniques and concepts.
Experience in implementing statistical modeling and machine learning methods.
Experience applying optimization algorithms offline and online.
Familiarity with deep learning, NLP, reinforcement learning, combinatorial optimization, etc.
Domain Knowledge and Technical Background: 
Experience in the mining technical field specifically on mine operations, mine control process, modular dispatch, fleet management systems, mine planning/design, and asset management.
Experience on operation and optimization of mining vendors’ applications for operations, modular dispatch, fleet management, mine planning, work management, and condition monitoring.
Experience using and processing mining vendors’ data sources for operations, dispatch, fleet management, mine planning, work management, and condition monitoring.
Business, communication, and collaboration skills:
Proficiency in defining and communicating business problems and opportunities against the objective of introducing solutions and improvements.
Demonstrated, well-developed judgment and problem-solving skills with an emphasis on product development.
Ability to promote vision and play a key role in achieving client satisfaction. 
 Ability to work well as part of a team, a diplomat, and resilience. 
Strong verbal and written communication skills that work effectively with technical and non-technical audiences. 
Fluent English (verbal and written) is a must, with desirable French. 

Software and Tools Proficiency:

Familiarity with statistical and data mining techniques: GLM/Regression, Random Forest, Boosting, Trees, text mining, social network analysis, etc. 
Experience querying databases and using statistical computer languages: Python, SQL, R, etc. 
Experience creating and using advanced machine learning algorithms and statistics: regression, simulation, scenario analysis, modeling, clustering, decision trees, neural networks, etc. 
Experience visualizing/presenting data for stakeholders using: Periscope, Business Objects, D3, ggplot, etc. 
Additional Attributes: Multi-tasking and excellent management of personal time and priorities. A drive to learn and master new technologies and techniques

General Accountability:

Proactively identify and champion machine learning initiatives that are highly applicable and can innovate practices within the mining industry in the mining and resource development domains.
Engage with Asset leadership to precisely understand specific business challenges, ensuring that these problems can be addressed using state-of-the-art analytics and AI solutions.
Leverage the latest methodologies in deep learning, reinforcement learning, and AI to craft effective solutions for prevailing business issues.
Play an instrumental role in mentoring and guiding other data scientists, fostering their professional development by enhancing their knowledge and skill sets.
Work in with data engineers, machine learning engineers, and designers to architect and implement holistic analytics solutions for internal clients, ensuring these solutions bring about tangible, positive real-world impacts.
Actively participate and contribute in a diverse, multi-disciplinary team environment, seamlessly collaborating with professionals from data science, data engineering, business, and design domains.
Oversee and govern data models provided by external consultants to ensure consistency, reliability, and alignment with company standards.
Maintain and monitor machine learning operations, ensuring efficient execution, up-to-date model performance, and prompt troubleshooting of any issues.
Establish and enforce stringent test protocols and conduct advanced studies for validating or rejecting hypotheses during the rollout of technological solutions related to decision-making processes.
Data Analysis: Analyze large datasets to extract meaningful insights and trends using, maintaining and improve the internal technology stack.
Machine Learning Model Development: Design, develop, and deploy machine learning models tailored to specific business challenges.
Optimization: Refine algorithms and models for improved accuracy and efficiency.
Collaboration: Work closely with business units, data engineers, and other stakeholders to define and refine project requirements.
Reporting: Present findings and insights to both technical and non-technical audiences in a clear and concise manner.
Continuous Learning: Stay updated with the latest developments in the field of data science, machine learning, and AI.
Data Governance: Ensure data quality and integrity. Establish and enforce data handling and privacy protocols.
Mentoring: Guide and upskill junior data scientists and analysts in best practices, techniques, and methodologies.
Tool and Platform Selection: Recommend and assist in the selection of appropriate tools and platforms for specific data tasks.
Solution Scaling: Scale models to handle larger datasets, ensuring they remain efficient in real-world scenarios.
Prototyping: Rapidly develop prototypes to test and validate new methodologies or concepts.
Model Maintenance: Monitor the performance of live models, ensuring they continue to operate as expected, and adjust as needed.
Stakeholder Communication: Engage regularly with stakeholders to ensure data initiatives align with business goals and objectives.
Risk Management: Identify potential risks in data-driven solutions and implement strategies to mitigate them.
Testing and Validation: Rigorously test new models and methods, ensuring their reliability before full-scale implementation.
Documentation: Document methodologies, insights, and findings comprehensively for future reference and for other team members using Git and internal Glencore policies.
Operational Integration: Work with IT and operations teams to integrate machine learning solutions into business operations.
Strategic Planning: Assist in the strategic planning of data initiatives, ensuring they align with the company’s long-term goals.

Application email or URL: http://www.glencore.com
Join Jobs South Africa

Apply for this Job

To apply for this job please visit www.glencore.com.