Data & ML Engineer at Hire Resolve

Main purpose of the role: 

• The Data & ML Engineer delivers the technical implementation of Data Transformation initiative under the direction of the Data Engineering Manager. The role owns whole data products from end to end, from ingestion and modelling through to datasets ready for machine learning, across the SSOT and central asset management platforms. 
• Working within the technical shared services team, the Engineer translates strategic direction into concrete,
• scalable solutions for a defined domain, operating with minimal supervision.

Responsibilities: 
Data Engineering

• Design and own modular, reusable ingestion and orchestration across API, SQL stored procedures and ETL/ELT for a domain, ensuring reliable flow into the SSOT from sources such as CAMs, ERP, OT and IoT systems and SharePoint.
• Design coherent data models and feature pipelines that support reporting, analytics and machine learning.
• Own the operational health of the domain, including monitoring, alerting and incident resolution, with advanced SQL and performance tuning.

Machine Learning

• Develop and evaluate machine learning models and algorithms such as forecasting, anomaly detection and neural networks, using established libraries and managing overfitting and drift.
• Design data structures and feature pipelines that make data applicable for machine learning, and integrate models into data workflows.
• Implement MLOps for own use cases, covering data and model versioning, CI/CD, monitoring and retraining.

Governance and Ownership

• Own whole data products from end to end for a domain and operate with minimal supervision.
• Make scalable architectural decisions and fill gaps independently, confirming assumptions on larger decisions.
• Apply data governance, security and IT standards, and maintain structured change management including approvals and rollback.

Platform Ownership

• Own AVEVA PI and CAMs for a site or domain, designing Asset Framework element templates and hierarchies and developing calculations within CAMs.
• Oversee asset onboarding and offboarding across the lifecycle, ensuring accurate registration, configuration and removal, and aligning asset data with reporting frameworks and dashboards.
• Configure notifications and event frames, maintain PI interfaces and the integration into the SSOT, and resolve discrepancies to uphold data integrity.

Team Dynamics

• Explain technical choices and their implications to stakeholders outside the technical team.
• Coordinate across divisions for a domain and enforce agreed standards and timelines.
• Mentor associates and review their work.
• Introduce new skills and use cases to the team to encourage collaborative learning.

Skills & Competencies: 

• Strong Python and advanced SQL, including performance tuning and schema and index design, with C# an advantage.
• Proven design of ingestion frameworks, integrations and data models for a domain, with scalable architectural decision making.
• Solid machine learning foundations plus practical MLOps, and the ability to develop and evaluate models and algorithms using established libraries.
• Working ownership of AVEVA PI and CAMs, including Asset Framework modelling, interfaces, alarms and event frames.
• Works independently, with strong engineering discipline and the ability to explain technical choices to a general audience.

Minimum Requirements

• Degree in Computer Science, Information Systems, Engineering, Mathematics or a related field.
• 5 to 7 years in data engineering or data platform development at a mid level, with 5 or more years accepted where there is clear evidence of independent delivery ownership.
• Hands on responsibility for API integration, ETL/ELT orchestration, data modelling and production operations.
• Strong SQL and Python, with experience in ETL tooling and automation frameworks, and practical experience developing machine learning models and integrating them into workflows.

Advantageous

• Hands on AVEVA PI configuration and integration, such as PI Integrator or APIs.
• Machine learning models in production and associated MLOps tooling, with deep learning exposure such as TensorFlow and PyTorch.
• Data lakes and big data architectures, and orchestration tools such as Airflow, Prefect or Azure Data Factory.
• Power Apps and Power Automate, and energy sector or industrial and IoT data experience.