Data & ML Engineer
Confirmed on the employer's own hiring board on Sep 29, 2026. First seen by Alion on Sep 29, 2026. Simplify HR scores B on the Alion truth index.
A leading independent power producer (IPP) focused on developing, owning, and operating clean and reliable electricity generation across Africa is seeking a Data & ML Engineer who will drive the technical implementation of the company's Data Transformation initiative.
Responsibilities:
Ingestion & Orchestration: Design and maintain modular pipelines (API, SQL, ETL/ELT) integrating sources like CAMs, ERP, OT/IoT, and SharePoint into the SSOT.
Data Modeling: Develop robust schemas and feature pipelines supporting analytics, reporting, and ML.
Operational Health: Manage domain monitoring, alerting, incident resolution, advanced SQL performance tuning, and schema design.
Model Development: Build, evaluate, and fine-tune ML models (forecasting, anomaly detection, neural networks) using standard libraries, actively managing overfitting and drift.
Pipeline Integration: Embed feature engineering and model scoring into automated data workflows.
MLOps Delivery: Implement end-to-end MLOps for domain use cases, including versioning, CI/CD, deployment, monitoring, and automated retraining.
Configuration: Own AVEVA PI and CAMs for the domain; design PI Asset Framework (AF) element templates, hierarchies, and internal calculations.
Lifecycle Management: Oversee asset onboarding/offboarding, ensuring accurate data registration, configuration, and alignment with reporting frameworks.
Integrations & Alerts: Configure notifications, event frames, and PI interfaces to maintain high data integrity across SSOT integrations.
End-to-End Delivery: Function as single-point-of-contact for domain data products, making scalable architecture decisions and filling technical gaps independently.
Standards & Compliance: Enforce data governance, security, IT standards, and structured change management (approvals, rollback plans).
Collaboration & Mentorship: Translate complex technical concepts for non-technical stakeholders, coordinate cross-divisional timelines, review associate work, and mentor team members on emerging practices.
Minimum Requirements:
Education: Bachelor’s degree in Computer Science, Information Systems, Engineering, Mathematics, or a related field.
Experience: 5-7 years in data engineering or data platform development (5+ years acceptable with strong evidence of independent delivery ownership).
Technical Experience: Practical hands-on ownership of API integration, ETL/ELT orchestration, data modeling, and production operations.
Tooling: Strong SQL and Python skills, ETL/automation frameworks, and experience integrating ML models into production workflows.
Programming & Querying: Strong Python and advanced SQL (schema design, indexing, performance tuning). C# is an advantage.
Data Architecture: Proven track record designing scalable ingestion frameworks, integrations, and enterprise data models.
ML & MLOps: Solid theoretical ML foundations combined with practical production deployment and MLOps practices.
Industrial Platforms: Hands-on experience configuring AVEVA PI (Asset Framework, interfaces, event frames) and CAM platforms.
Soft Skills: High autonomy, technical discipline, cross-functional communication, and stakeholder management.
Advantageous
AVEVA PI: Hands-on integration via PI Integrator or PI Web API / SDKs.
Advanced ML: Production deep learning exposure (e.g., TensorFlow, PyTorch) and MLOps tooling.
Big Data & Orchestration: Experience with Data Lakes, Azure Data Factory, Airflow, or Prefect.
Domain & Low-Code: Energy/industrial IoT experience, plus familiarity with Power Apps and Power Automate.
Benefits:
Competitive salary based on experience (salary can potentially be more based on experience/skills)
IF you meet the above requirements and want to make a career-changing move, apply today by emailing your CV to [email protected]