Maintenance Engineer - Data Science Projects
Summary
A Maintenance Engineer at a consulting company in Johannesburg keeps production data science systems (predictive models, data pipelines, dashboards, APIs) reliable and up to date: monitoring health, diagnosing drift and degradation, automating health checks, patching environments, and supporting incident response using Python, R, SQL, CI/CD, Docker, and cloud platforms.
A leading consulting company and aforward-thinking team is looking for a Maintenance Engineer to join their team in Johannesburg, GP.Your main mission will be to ensure the continued reliability, performance, and evolution of advanced data science systems. You'll play a critical role in supporting the long-term value of deployed models, data pipelines, dashboards, and APIs - keeping them accurate, stable, and aligned to business needs. This position blends technical vigilance with continuous improvement and stakeholder collaboration.
Key Responsibilities
- Monitor the health and performance of production data science systems, including predictive models, dashboards, and data pipelines.
- Diagnose issues such as data drift, performance degradation, or infrastructure instability, and implement timely fixes.
- Automate monitoring tasks and health checks related to data quality, forecast accuracy, and pipeline execution.
- Update and patch environments and applications, ensuring smooth operation across versions and dependencies.
- Collaborate with engineers and data scientists to refactor and optimize code for long-term maintainability.
- Maintain detailed documentation and change logs to ensure knowledge sharing and traceability.
- Support incident response, including root cause analysis and post-incident improvements.
- Ensure compliance with all applicable data privacy, security, and regulatory standards.
Requirements
- Bachelor's degree in Computer Science, Engineering, Mathematics, or a related field.
- Minimum 2 years' experience in a data engineering, MLOps, or system maintenance role.
- Solid understanding of data science production workflows, including pipelines and model lifecycle.
- Proficient in Python and R with strong debugging and refactoring capabilities.
- Confident in SQL and managing large-scale datasets in production.
- Experience with CI/CD, Git, and containerization tools like Docker.
- Familiarity with cloud infrastructure (AWS, GCP, or Azure) and DevOps best practices.
- Strong analytical, problem-solving, and communication skills.