Description

You will develop and deploy predictive maintenance models for asset health monitoring and Residual Useful Life (RUL) calculation.

This role is on-site.

Responsibilities

• Build end-to-end AI/ML pipelines including data pre-processing, feature engineering, modeling, and deployment.
• Apply time series techniques such as Fourier transforms, Fast Fourier transforms, and Wavelets for signal analysis.
• Develop predictive models using ARIMA, SARIMA, LSTM, RNN, and Autoencoders.
• Execute statistical signal processing for data cleaning, correlation, partial correlation, and factor analysis.
• Estimate model orders and delays from data to refine performance based on specific metrics.

Required Skills

• 10+ years of experience in data science and machine learning.
• Expertise in Python and libraries including Keras, Numpy, Pandas, Scikit-learn, Scipy, and TensorFlow.
• Proven experience with time series modeling, prediction, and probabilistic forecasting.
• Hands-on knowledge of algorithms such as Linear Regression, Naive Bayes, Decision Trees, Random Forest, SVM, PCA, and PLS.
• Experience working with large-scale time series data.
• Proficiency in AWS environments.
• Experience using Linux platforms and Git/Gitlab.

Preferred Skills

• Experience developing and deploying models using AWS SageMaker.
• Background working with electrical utility companies or electric vehicle manufacturers.

Key Skills

Education

Any Graduate