Industrial AI Engineer: Predictive Maintenance

HYRED; Singapore; On-site; SGD 90,000 - 180,000; Full time

Job summary

HYRED is seeking an AI Engineer in Singapore to develop and deploy machine-learning solutions from real-world industrial sensor data. You will build models for predictive maintenance and fault diagnosis, preprocess large time-series datasets, and translate research into production-ready workflows.

This hands-on role emphasizes putting models into production to improve asset reliability and operational performance, with close collaboration to data pipelines and engineering teams.

Qualifications

• Bachelor’s/Master’s degree in CS/AI/DS or related field.
• At least 3 years of hands-on ML model development and deployment.
• Experience with time-series data and industrial sensor datasets.

Responsibilities

• Develop ML and DL models for predictive maintenance, anomaly detection and fault diagnosis.
• Preprocess and analyze large-scale time-series and industrial sensor data.
• Work with signals such as vibration and temperature for model inputs.
• Build scalable models for real-time or low-latency prediction.
• Monitor model performance on production data and iterate.
• Collaborate with engineering to improve data pipelines and model accuracy.
• Design experiments and validate hypotheses with machine data.
• Translate academic research into production-ready approaches.
• Document models, methods and performance for stakeholders.

Skills

Machine learning

Time-series analysis

Python/R/Java

Signal processing

Noisy real-world data handling

Education

Bachelor's or Master's in Computer Science/AI/Data Science or related

Tools

TensorFlow

PyTorch

Scikit-learn

AWS

GCP

Azure

Job description

HYRED is seeking an AI Engineer in Singapore to develop and deploy machine-learning solutions from real-world industrial sensor data. You will build models for predictive maintenance and fault diagnosis, preprocess large time-series datasets, and translate research into production-ready workflows.

This hands-on role emphasizes putting models into production to improve asset reliability and operational performance, with close collaboration to data pipelines and engineering teams.