Bestkaam Logo
Back to Jobs
SteerLean Consulting

Data Scientist – Utilities & Energy Analytics

Actively Reviewing

SteerLean Consulting

Mumbai Full-Time 4–8 yrs exp Posted 1 day ago  · Apply by Sep 14, 2026
About The Role

We are seeking a highly technical Data Scientist to drive a large-scale AI/ML transformation for one of India's largest electricity distribution utilities.

Important Note: This is a hands-on coding and development role focused on classical Machine Learning, statistical modeling, and predictive analytics. Candidates whose primary or sole experience is in Generative AI (GenAI) will not be considered. You must be able to write robust ML code from scratch. The core mission is to build and deploy advanced models for electricity theft detection, anomaly identification, and revenue protection using millions of smart meter and consumer data points.

Core Responsibilities

  • Hands-On ML Coding: Develop, train, and optimize classification and predictive models for anomaly detection and risk-scoring frameworks.
  • Data Engineering at Scale: Write complex feature engineering logic and build scalable ETL pipelines using AMI, billing, collection, and inspection data.
  • MLOps & Production: Deploy models into production (REST APIs/batch jobs) and manage continuous monitoring, drift detection, and automated retraining pipelines.
  • Analytics & Business Impact: Translate analytical outputs into actionable dashboards for tracking theft detection performance and revenue recovery.

Required Skills & Qualifications

  • Education: Bachelor's or Master's degree in a highly quantitative discipline like Data Science, Computer Science, Statistics, Mathematics, or Engineering.
  • Domain Expertise: Minimum 5+ years of experience, preferably within Electricity Distribution Companies (DISCOMs), Smart Metering Projects, or Utility Analytics.
  • Programming Languages (Mandatory): Advanced, production-level coding proficiency in Python and SQL.
  • Machine Learning Stack: Proven track record building custom models using Scikit-Learn, XGBoost, TensorFlow, and PyTorch.
  • Big Data Ecosystem: Strong experience with Databricks, Apache Spark, and cloud-based data lake architectures.