Load Forecasting Engineer

About the Role

We are looking for an experienced Load Forecasting Engineer to develop and validate advanced load forecasting solutions for electrical distribution networks from 66 kV downstream to edge points.

The role focuses on predicting future electricity demand to support grid planning, infrastructure optimization, demand management, and DER integration, including solar PV, electric vehicles, and energy storage.

The ideal candidate should combine strong power-system and distribution-network knowledge with expertise in time-series forecasting, AI/ML modeling, and data-driven analysis.

Key Responsibilities

• Develop and validate short-term and long-term load forecasting models for electrical distribution networks.
• Apply time-series, regression, and AI/ML techniques to improve forecast accuracy and reliability.
• Implement advanced forecasting approaches such as LSTM networks and attention mechanisms where appropriate.
• Process and analyze smart-meter data, including data cleaning, missing-data handling, outlier detection, and aggregation.
• Map load data spatially across relevant network assets, including substations and feeders.
• Incorporate external demand drivers such as temperature, humidity, holidays, weekends, and economic indicators.
• Develop probabilistic forecasts and stochastic scenarios to assess forecasting uncertainty and future demand risks.
• Evaluate the impact of solar, EVs, energy storage, and other DERs on load patterns and network demand.
• Establish appropriate forecasting benchmarks and validation methods to assess model performance.
• Collaborate with engineering, data science, and software teams to integrate forecasting models into distribution-grid planning and analytical applications.
• Translate engineering requirements into forecasting methodologies and computational models.

Required Qualifications

• M.Tech / Ph.D. in Power Systems, Electrical Engineering, or a related field.
• 510 years of relevant professional experience in load forecasting, distribution systems, power-system planning, or a related domain.
• Strong understanding of electrical distribution networks, load behavior, and demand patterns.
• Proven experience in developing and validating electricity load forecasting models.
• Strong analytical and problem-solving capabilities with the ability to work with large-scale and high-resolution datasets.
• Proficiency in Python and relevant data analytics or machine-learning frameworks.
• Ability to communicate technical findings clearly and collaborate with engineering, data science, and software teams.

Core Technical Skills

• Short-Term & Long-Term Load Forecasting
• Time-Series & AI/ML Modeling
• LSTM, Attention-Based & Regression Models
• Smart-Meter Data Processing & Analysis
• Substation & Feeder-Level Load Analysis
• Exogenous Variable Integration
• Probabilistic Forecasting & Uncertainty Analysis
• Stochastic Scenario Generation
• DER Impact Assessment

Preferred / Additional Expertise

• Experience with distribution-level forecasting across substations, feeders, and downstream/edge points.
• Experience with spatial/network-based load mapping and distribution-system datasets.
• Exposure to forecasting challenges associated with high solar PV, EV, and energy-storage penetration.
• Knowledge of utility planning and distribution-grid applications where load forecasts support capacity and infrastructure decisions.
• Experience working with large-scale smart-meter or AMI datasets.
• Understanding of grid modernization and data-driven distribution-system applications.
• Familiarity with power-system simulation or distribution-network analysis tools would be an advantage.

Ideal Candidate

The ideal candidate is a Load Forecasting Engineer who can combine electrical distribution-system knowledge with advanced forecasting and AI/ML capabilities.

The candidate should be comfortable working with complex network data, developing reliable forecasting models, assessing uncertainty and changing demand patterns, and collaborating with multidisciplinary technical teams.