Machine Learning Engineer

Location: Gurgaon
Experience Level: 13 Years
Department: Technology
Employment Type: Full-Time
About Us
GNA Energy is a technology-driven energy analytics company building intelligent solutions for Indias evolving power markets. We combine domain expertise with advanced analytics, AI, and forecasting models to enable smarter decision-making across the energy ecosystem.
Our focus lies in developing data-driven tools that support market participants, regulators, and energy stakeholders in navigating dynamic market conditions. With innovation at our core, we are shaping the future of predictive intelligence in the power sector.
About The Role
We are seeking a Machine Learning Engineer with 1-3 years of experience in developing, validating, and deploying machine learning models. The analyst may work across one or multiple domains, including (A) time series forecasting, (B) AI agents for the power sector, and (C) RAG-based document intelligence.
The role requires strong Python skills and the ability to take full ownership of the project lifecycle: from data sourcing and preparation to modelling, output delivery, and generating meaningful business outcomes for internal and external clients.
The ideal candidate should have a strong foundation in handling large datasets and machine learning fundamentals.
This is a hands-on, execution-focused role requiring the ability to translate complex datasets into scalable ML solutions that support forecasting and data-driven decision-making in the power sector.
Key Responsibilities
Time Series Forecasting

• Build and validate time-series forecasting models using statistical, ML, and deep-learning methods.
• 
  Contribute to forecasting frameworks for short-, medium-, and long-term horizons.
  

AI Agents for Power Sector (Structured Datasets)

• Work with structured datasets from grid, energy, and power-sector systems.
• Design and refine AI agent workflows for operational intelligence and decision support.
• Develop end-to-end pipelines integrating data, models, and agent-based automation.
  

RAG (Retrieval-Augmented Generation) & Document Intelligence

• Build and optimise RAG systems for document retrieval, summarisation, and analysis.
• Work with embeddings, vector databases, retrieval optimisation, and evaluation.
• Improve contextual accuracy, precision, and recall of RAG-based solutions
  

Candidate will take ownership for the complete project cycle: from data sourcing, cleaning, preparation, modelling, evaluation, deployment, and insights delivery. This will require:
Perform data preprocessing, feature engineering, and exploratory data analysis (EDA).

• Collaborate with cross-functional teams, including data engineering to setup data pipelines, and business teams to validate outcomes.
• Conduct model validation, hyperparameter tuning, and performance monitoring.
• Support deployment of models into production environments.

• Looking to get Placed? Try our Placement Guarantee Plan

  Get Hired
  Communicate analytical insights clearly to internal stakeholders.
• Stay updated with emerging ML techniques and industry best practices.
  

Essential
Qualifications & Skills

• Bachelors or Masters degree in Computer Science, Data Science, Statistics, Mathematics, Engineering, or related quantitative discipline.
• 1-3 years of experience in Machine Learning / Data Science roles.
• Strong understanding of supervised and unsupervised learning techniques.
• Experience in one or more of the following domains: time-series forecasting, AI agent development, or RAG-based document intelligence systems.
• Proficiency in Python, with hands-on experience in:
• scikit-learn
• TensorFlow / PyTorch
• pandas / NumPy
• statsmodels / Prophet
• Knowledge of model evaluation techniques and validation frameworks.
• Self-driven and proactive with the ability to understand and solve business problems, take ownership of projects, experiment with new approaches, iterate quickly, and ensure outcomes are meaningful for the business.
• Ability to work in a fast-paced, collaborative environment.