Job
Description
Job Designation - Full Stack Data Engineer - AI/ML Location - Mundhwa, Pune Years of experience - 5 years Key Responsibilities: · Model Development & Deployment: Develop and deploy ML/DL models for predictive maintenance, anomaly detection, forecasting (e.g., energy production, equipment failure), and performance optimization of renewable assets. · Advanced Analytics: Perform exploratory data analysis (EDA), hypothesis testing, and statistical modeling to identify trends, patterns, and correlations in large datasets. · Collaboration with Engineers: Work closely with data engineers to design and validate data pipelines that feed ML models and analytics dashboards. · Feature Engineering: Engineer meaningful features from sensor and operational data, integrating diverse data sources such as IoT, weather, and operational logs. · Model Monitoring & Optimization: Monitor model performance post-deployment and implement continuous learning and model retraining pipelines (MLOps). · Business Understanding: Translate business objectives into analytical solutions and communicate findings effectively with both technical and non-technical stakeholders. · Tooling & Automation: Use platforms like MLflow, Airflow, and containerization tools (Docker/Kubernetes) to automate ML workflows. · Visualization & Reporting: Create dashboards and visualizations using PowerBI, Tableau, or open-source tools to present insights and model outputs to business users. Required Skills and Qualifications: · Education: Bachelor’s or Master’s degree in Data Science, Computer Science, Engineering, Applied Mathematics, or a related field. · Experience: 5+ years of experience in data science roles with a strong portfolio of delivered projects, ideally in the energy, manufacturing, industrial IoT, or sustainability domains. · Technical Proficiency: · Programming: Python (must), Pyspark, R (optional) · Libraries/Frameworks: scikit-learn, XGBoost, TensorFlow/PyTorch, pandas, NumPy, MLflow,NLP, LLMs like BERT, GPT, T5, Mllib, FastAPI / Flask · Big Data Tools: PySpark, Apache Spark · Databases: PostgreSQL, Dynamo, MS SQL, NoSQL (MongoDB, Cassandra) · Cloud Platforms: AWS (preferred), Azure or GCP · Orchestration: Apache Airflow, AWS Step Functions, Lambda · Version Control: Git Show more Show less
