Industrial IoT ML Engineer — Smart Maintenance & Optimization

Atlas Copco Holding GmbH; Antwerpen; Hybride; EUR 70 000 - 100 000; Plein temps

Avantages offerts par ce poste

Health insurance

Paid leave

Retirement benefits

Résumé du poste

Atlas Copco Group is seeking an Applied Machine Learning Engineer in Antwerp to transform sensor data from connected products into optimization and smart-maintenance models. You will work across the global connectivity ecosystem to deliver measurable value for customers.

You will analyze vibration, temperature, pressure, and operational data using time- and frequency-domain techniques, applying anomaly detection, predictive maintenance, classification, clustering, and forecasting to drive

Qualifications

• Master's degree in engineering (Electronics, Computer Science, or equivalent)
• Hands-on with signal processing and machine learning applied to sensor data
• Strong interest in mechanical systems (compressors, dryers, chillers or similar) and domain exploration
• Enjoy working in diverse, international teams across functions
• Problem-solving mindset with a drive to innovate and improve

Responsabilités

• Develop and enhance models focused on energy efficiency, performance optimization, and smart maintenance for connected products.
• Integrate, validate, and deploy optimization algorithms within the Smart Events engine and connectivity platform.
• Collaborate with engineering, marketing, and operations to shape roadmaps and deliver solutions that create customer value.

Connaissances

Python

PySpark

Databricks

Pandas

Scikit-learn

MLflow

Signal processing

Machine learning

Formation

Master's degree in engineering

Outils

Databricks

Description du poste

Atlas Copco Group is seeking an Applied Machine Learning Engineer in Antwerp to transform sensor data from connected products into optimization and smart-maintenance models. You will work across the global connectivity ecosystem to deliver measurable value for customers.

You will analyze vibration, temperature, pressure, and operational data using time- and frequency-domain techniques, applying anomaly detection, predictive maintenance, classification, clustering, and forecasting to drive