Data Scientist - ML in Production for Logistics & Finance

Scan Global Logistics; Hinoba-an; On-site; PHP 900,000 - 1,500,000; Full time

Job summary

Scan Global Logistics seeks a data scientist to work on the Microsoft data platform, focusing on decisions changed rather than models trained. You will frame business questions with stakeholders and guide models from proof of concept to deployed, monitored solutions in logistics operations, finance and commercial.

You will build features and data pipelines on lakehouse and warehouse data using Python and SQL, put models into production with MLflow and managed endpoints, monitor drift and data

Qualifications

• Master's or Bachelor's degree in data science, statistics, computer science, mathematics or another quantitative field.
• Microsoft Certified: Azure Data Scientist Associate; Fabric Analytics Engineer Associate or Azure AI Engineer Associate is an advantage.
• At least three years of applying machine learning and statistical methods to business problems.

Responsibilities

• Frame business questions with stakeholders, then build, validate and deploy models in Azure Machine Learning and Microsoft Fabric.
• Engineer features and data pipelines over lakehouse and warehouse data using Python and SQL.
• Put models into production with MLflow and managed endpoints, and monitor them for drift, data quality and performance.
• Communicate findings through Power BI and written analysis, so that the recommendation is clear to a non-technical audience.
• Partner with the AI team on evaluating large language model solutions, and apply data governance and privacy requirements to every dataset used.

Skills

ML applications

Statistical methods

Data analysis

Education

Master's or Bachelor's degree in a quantitative field

Tools

Azure Machine Learning

Microsoft Fabric

MLflow

Power BI

Job description

Scan Global Logistics seeks a data scientist to work on the Microsoft data platform, focusing on decisions changed rather than models trained. You will frame business questions with stakeholders and guide models from proof of concept to deployed, monitored solutions in logistics operations, finance and commercial.

You will build features and data pipelines on lakehouse and warehouse data using Python and SQL, put models into production with MLflow and managed endpoints, monitor drift and data