Machine Learning Engineer - Acoustic Fault Detection
Description
About the Role:
We are looking for hands-on Machine Learning Engineers to develop AI/ML solutions for acoustic-based fault detection, anomaly detection and predictive maintenance.
Total Experience: 2 - 6 years
Key Responsibilities:
- Develop ML models for fault detection, anomaly detection, and fault classification using acoustic and sensor data
- Work with DSP engineers to preprocess acoustic signals and extract meaningful features
- Build, train, evaluate, and optimize ML models for real-world deployment
- Analyze field data and improve model accuracy through continuous learning
- Develop data pipelines for model training and inference
- Support deployment, monitoring, and performance evaluation of production models
- Collaborate with backend, DSP, and frontend teams
Key Requirements:
- Strong proficiency in Python, NumPy, Pandas, Scikit-learn and PyTorch / TensorFlow.
- Hands-on experience in Machine Learning, Deep Learning and model development.
- Strong understanding of time-series analysis, sensor data processing and feature engineering.
- Experience working with acoustic/ audio/ speech/ voice/ vibration/ Industrial sensor data is preferred.
- Knowledge of DSP concepts such as FFT, Spectrograms and Wavelet Transforms is an advantage.
- Experience in model evaluation, optimization and deployment pipelines.
- Exposure to FastAPI / Flask and SQL / NoSQL databases is an added advantage.
- Background in Predictive Maintenance, Industrial AI, Industrial IoT or Railways is preferred.
What we are looking for:
Candidates who can take ML models beyond experimentation and contribute to real-world production deployments.
Skills
Sign in to read and join the discussion.