Job highlights

- Perform data pre-processing and feature engineering,including data cleaning,normalization,aggregation,and creation of domain-relevant features . Design and maintain data pipelines for both real-time streaming data and batch data processing to support analytics and ML workflows .
- Experience working with industrial,manufacturing,energy,or IoT datasets . .

This role focuses on applying Artificial Intelligence and Machine Learning techniques to solve real-world industrial and operational challenges. The position involves working with large-scale sensor, telemetry, and time-series data to develop intelligent analytics solutions that improve system efficiency, reliability, and performance.

Roles and Responsibilities

- Design, develop, and deploy machine learning models for industrial and operational analytics use cases, ensuring solutions are scalable, robust, and production-ready
- Develop predictive maintenance models to anticipate equipment failures and reduce unplanned downtime across industrial systems
- Build anomaly detection solutions to identify abnormal patterns in sensor and operational data, enabling early fault detection and proactive intervention
- Develop forecasting models for load, energy consumption, performance metrics, and operational trends using historical and real-time data
- Analyse large-scale sensor, telemetry, and time-series datasets , identifying patterns, correlations, and performance drivers
- Perform data pre-processing and feature engineering , including data cleaning, normalization, aggregation, and creation of domain-relevant features
- Design and maintain data pipelines for both real-time streaming data and batch data processing to support analytics and ML workflows
- Collaborate with cross-functional teams , including product, engineering, and domain experts,



to translate business and operational problems into AI-driven solutions
- Optimize machine learning models for accuracy, computational efficiency, scalability, and deployment constraints
- Deploy models into production environments and integrate them with existing systems and applications
- Monitor model performance in production , track accuracy drift, data drift, and system behaviour, and implement continuous improvement strategies
- Document model logic, assumptions, workflows, and technical decisions to ensure maintainability and knowledge sharing

Requirements
- Strong foundation in Machine Learning and Statistics , including supervised and unsupervised learning techniques
- Proficiency in Python , with hands-on experience using libraries such as NumPy, Pandas, Scikit-learn, and PyTorch and/or TensorFlow
- Experience working with time-series data , including trend analysis, seasonality, and temporal modeling techniques
- Knowledge of predictive modeling, anomaly detection, and forecasting methods applicable to operational and industrial datasets
- Experience in data preprocessing and feature engineering , particularly for noisy and high-frequency data
- Familiarity with SQL and/or NoSQL databases for data extraction, storage, and analysis
- Understanding of data pipelines and ML workflows , including data ingestion, model training, validation, and deployment
- Positive problem-solving, analytical, and debugging skills , with the ability to work on complex and ambiguous data challenges

Good to have
- Experience working with industrial, manufacturing, energy, or IoT datasets
- Exposure to real-time data processing frameworks and streaming architectures
- Familiarity with cloud-based ML platforms and scalable deployment practices
- Understanding of model monitoring, versioning, and MLOps concepts

📌 AI / ML Engineer - Industrial Analytics (Pune)
🏢 greenovative energy
📍 Pune