Vestas - Data Scientist ( 6-0 yrs ) (Bengaluru)

Vestas is the world leader in wind technology and a driving force in the development of the wind power industry. Vestas core business comprises the development, manufacture, sale, marketing, and maintenance of wind turbines. Come and join us at Vestas! Product Applications & Controls R&D; > Modelling & Analytics Module > Plant Monitoring & Reliability Plant Monitoring & Reliability Sub Module, within Modelling & Analytics Module (M&A;), Part of Vestas Power Solutions, is responsible for the products and services related to Vestas Monitoring and Reliability solutions and offerings. We have an experienced and diverse team that consists of everything from Health Monitoring Engineers/Specialists and Reliability Engineers/ Specialists, Data engineers, Data Analysts, and Data Scientists. The department is responsible for developing advanced Plant Monitoring Products & Solutions - Health Monitoring, Condition Monitoring, Power Quality Monitoring, Reliability and VTMs. This ranges across real-time data collection from thousands of power plants with Health Monitoring systems, and data analytics on a Health Monitoring & Reliability setup supporting multiple data applications, Diagnostics, Monitoring solutions for our customers. The goal is to bring down the cost of energy by leveraging the vast amount of data that Vestas collects and stores from power plants around the globe. Responsibilities - Apply statistical modeling, machine learning, and deep learning techniques on multivariate time-series data to develop predictive, modular, and scalable condition monitoring systems for wind turbines - Design and implement robust model management processes to govern the entire ML lifecycle, including development, deployment, and operations, within a cross-functional predictive maintenance architecture - Define accurate, statistically sound summary metrics to evaluate and benchmark model performance effectively - Translate complex, statistically rigorous analyses into actionable insights and communicate findings to cross-functional teams, customers, partners, and executives to create measurable business impact - Work collaboratively within Agile teams comprising Data Scientists, Data Engineers, and Quality Engineers to research, develop, and deliver advanced analytical solutions that create business value - Interact with domain experts to understand real-world challenges and interpret approaches for practical, impactful solutions - Research and apply advanced ML techniques to improve prediction accuracy - Optimize models for scalability and performance in production environments - Ensure data quality, security, and compliance with organizational standards - Anticipate internal and external business issues, recommend best practices, and provide strategic guidance on product, process, or service improvements to overcome challenges - Represent Vestas within the industry and scientific community by building relationships, sharing knowledge, and promoting collaboration among peers Qualifications - Bachelor's/Master's / PhD in Computer Science / Data Science / Statistics / Mathematics / STEM / Similar specialization - Minimum 6+ years of experience in Data Science and frameworks, including proficiency with data preparation and data exploration techniques. This experience should also encompass - Application of machine learning techniques such as data mining, statistical analysis, deep learning, and anomaly detection - Extensive experience in analyzing large-scale condition monitoring datasets, including SCADA and CMS data, to derive strategic insights - Professional certification in Vibration Analysis - Proficient communication & presentation skills in English, both written and verbal Competencies - Advanced proficiency in Python, Pyspark and its libraries (Pandas, NumPy, Scikit-learn, TensorFlow/Keras, PyTorch, MLflow, etc.) - Experience with SQL and data manipulation - Solid understanding of machine learning and deep learning algorithms, statistical modeling, and predictive analytics - Good knowledge of cloud platforms, particularly Azure - Experience using Databricks for ML workflows and big data processing - Experience in building and managing CI/CD pipelines for machine learning models - Knowledge of model deployment, monitoring, and retraining strategies in production environments - Proficiency with version control systems (Git) & demonstrated ability to collaborate effectively in Scrum teams - Experience with time-series analysis and forecasting & Solid foundation in probability, statistics, and optimization techniques - Proficiency in designing and developing end-to-end production-ready ML pipelines using PySpark, Databricks, and cloud platforms What We Offer We offer you the opportunity to leverage your skills and to work in a multicultural and international company, where you have the possibility to improve your skills and develop professionally Additional Information Your primary workplace will be in Vestas