Design, develop, and deploy production-grade AI/ML models for compressor manufacturing and industrial equipment.

- Build end-to-end ML pipelines covering data ingestion, feature engineering, model training, deployment, monitoring, and continuous improvement.

- Develop machine learning solutions for:

1. Equipment health monitoring and Predictive maintenance

2. Remaining Useful Life (RUL) estimation

3. Anomaly detection, Fault diagnosis and root cause analysis

4. Process optimization

5. Energy efficiency optimization

6. Production quality prediction

- Analyze industrial time-series data collected from: Vibration sensors, Pressure sensors, Temperature sensors, Flow sensors, Motor current signals, SCADA/PLC systems, Industrial historians, Maintenance and service records, Alarm and event logs.

- Apply signal processing techniques such as FFT, spectral analysis, wavelet transforms, and statistical feature extraction for rotating equipment diagnostics.

- Develop scalable ML models capable of handling noisy, incomplete, and high-frequency industrial data.

- Collaborate with reliability engineers, maintenance teams, and customer SMEs to understand failure modes and operational constraints.

- Deploy models into production using MLOps best practices, ensuring monitoring, drift detection, automated retraining, and high system reliability.

- Build reusable feature engineering frameworks and model evaluation pipelines.

- Contribute to intelligent decision-support capabilities that enable recommendations for maintenance scheduling, process optimization, and autonomous operational improvements while maintaining safety and governance standards.