Data Scientist - Renewable Energy

Job Description

Mandatory Skills: Technical Expertise in Forecasting & Machine Learning: Strong experience in Wind and Solar power forecasting with time series modelling techniques like ARIMA / SARIMA . Proficiency in machine learning models like Regression, XGBoost, Random Forest, and neural networks like LSTMs . Experience with deep learning frameworks such as TensorFlow, PyTorch, or Keras for time series forecasting. Domain Knowledge in Renewable Energy & SCADA: Hands-on experience working with SCADA data , weather forecast data , and NWP models . Understanding of weather forecasting methodologies and their impact on power generation predictions. Programming & Data Engineering: Strong Python programming skills, with expertise in libraries like pandas, NumPy, scikit-learn, TensorFlow, PyTorch, and Statsmodels. Proficiency in SQL, Data pipeline development , and Cloud platforms (Azure, AWS, or GCP). Experience in building scalable data architectures for production-ready machine learning models. Model Evaluation & Accuracy Metrics: Knowledge of forecasting accuracy metrics (RMSE, MAE, MAPE etc.) and best practices for model evaluation. Responsibilities: Exploratory Data Analysis (EDA) & Data Processing: Perform in-depth EDA to identify patterns, trends, and anomalies in SCADA and weather data. Develop feature engineering pipelines for time series forecasting, including lag features, rolling statistics, and weather variable transformations. Handle data cleaning, transformation, and augmentation techniques for improving forecasting accuracy. Renewable Energy Forecasting: Develop and optimize models for wind and solar power forecasting using time series analysis, machine learning, and deep learning techniques. Work with Numerical Weather Prediction (NWP) models and generate weather forecast data for improving forecasting accuracy. Understand and process SCADA data for predictive analytics and forecasting model improvements. Model Development & Evaluation: Implement time series forecasting models, including ARIMA, ARIMAX, SARIMA, LSTMs, XGBoost, Random Forest, and other regression-based techniques. Evaluate models using forecasting accuracy metrics such as RMSE, MAE, MAPE. Optimize model hyperparameters and validate results using appropriate cross-validation techniques. Data Engineering & Cloud Integration: Design and develop data pipelines for ingesting, processing, and storing renewable energy data efficiently. Work with SQL databases, Azure Data Factory, AWS S3, or other cloud data storage solutions . Optimize model deployment for real-time and batch processing in a cloud environment. Productization & Architecture: Develop scalable and efficient machine learning pipelines for operationalizing forecasting models. Work on cloud-based architectures (Azure, AWS, GCP) to support model deployment and integration into production systems. Collaborate with software engineers and DevOps teams for seamless model integration into forecasting products. Role & responsibilities