Data Engineer with Machine Learning

DME Service Solutions; Philippines; On-site; PHP 900,000 - 1,500,000; Full time

Job summary

DME Service Solutions is expanding its workforce analytics function and seeks a Data Engineer who can work across pipeline architecture and forecasting model development. The role blends HRIS data, Azure cloud infrastructure, and applied machine learning to design and maintain enterprise-scale forecasting systems.

You will build and maintain Azure-based ELT pipelines, design ML and statistical models (XGBoost, Prophet, ARIMA, regression, random forest), monitor forecast accuracy, and translate

Qualifications

• 3-5 years of experience in Azure data engineering (Data Factory, Synapse Analytics, Databricks, Data Lake, Azure SQL).
• 3-5 years of experience with Python for ETL/ELT development, machine learning, and automation.
• Demonstrated proficiency in data modeling, data warehousing, and data integration best practices.
• Experience working cross-functionally with Operations, Workforce Management, and Business Intelligence teams.

Responsibilities

• Architect and maintain Azure SQL data models, ELT pipelines, and automated datasets supporting forecasting and HRIS reporting requirements.
• Design, build, and validate machine learning and statistical forecasting models (XGBoost, Prophet, ARIMA, regression, random forest).
• Own forecast accuracy, including variance monitoring, drift diagnosis, and model recalibration.
• Translate forecasting outputs into staffing strategy, including hiring requirements, overtime planning, leave capacity, and schedule risk.
• Develop and maintain the Power BI reporting layer supporting executive-level analytics.
• Represent forecasting data in Weekly and Monthly Business Reviews, presenting assumptions and recommendations to leadership stakeholders.

Skills

Python for ETL/ML

Data modeling

Cross-functional collaboration

Stakeholder communication

Tools

Azure Data Factory

Azure Synapse Analytics

Databricks

Azure Data Lake

Azure SQL

Power BI

Job description

Role Description

We are expanding our workforce analytics function and seeking a Data Engineer capable of operating across both pipeline architecture and forecasting model development. This role sits at the intersection of HRIS data, Azure cloud infrastructure, and applied machine learning, with responsibility for designing and maintaining the systems that enable enterprise-scale workforce forecasting.

Core Responsibilities

• Architect and maintain Azure SQL data models, ELT pipelines, and automated datasets supporting forecasting and HRIS reporting requirements
• Design, build, and validate machine learning and statistical forecasting models (XGBoost, Prophet, ARIMA, regression, random forest) using volume, AHT, shrinkage, and attendance data
• Own forecast accuracy, including variance monitoring, drift diagnosis, and model recalibration in response to changing business conditions
• Translate forecasting outputs into staffing strategy, including hiring requirements, overtime planning, leave capacity, and schedule risk
• Develop and maintain the Power BI reporting layer supporting executive-level analytics
• Represent forecasting data in Weekly and Monthly Business Reviews, presenting assumptions and recommendations to leadership stakeholders

Required Qualifications

• 3-5 years of experience in Azure data engineering (Data Factory, Synapse Analytics, Databricks, Data Lake, Azure SQL)
• 3-5 years of experience with Python for ETL/ELT development, machine learning, and automation
• Demonstrated proficiency in data modeling, data warehousing, and data integration best practices
• Experience working cross-functionally with Operations, Workforce Management, and Business Intelligence teams

Preferred Qualifications

• Experience with CI/CD pipelines, cloud cost optimization, and infrastructure automation
• Familiarity with MLOps practices and AI enablement initiatives
• Ability to communicate technical model behavior in clear business terms for non-technical stakeholders
• Ability to manage sensitive or high-stakes workforce discussions, including capacity constraints, leave restrictions, and staffing gaps, using data-driven reasoning