Data Scientist

Duties and Responsibilities:

• Forecasting Learning Algorithms using Machine Learning and optimization strategies to solve problems not limited to Energy Forecasting, Motor Fault Detection, Energy Disaggregation, and anomaly detection
• Forecast Optimization algorithms for Energy Storage
• Control Strategy Optimization for Building Automation i.e Smart Buildings
• Forecasting Algorithms and Optimization strategies for Building Energy Management (BEM) & Demand Response
• Discover the information hidden in vast amounts of data, and help us make smarter decisions to deliver even better products
• Applying data mining techniques, doing statistical analysis, and building high-quality prediction systems integrated with our products
• Suggest and develop innovative analytic methods that result in a technically superior product and/or create a competitive advantage, as well as meet design requirements and project timeline
• Lead research, evaluation, and recommendation of internal and external data sources and coordinate with a data resource
• Serve as the senior technical expert for leadership on data cleansing, variable creation, variable transformation, etc. As well as best-practices in the creation of analytic datasets
• Serve as the consummate technical expert in model development and validation analyses - from driving pragmatic practice of methods to devising novel solutions and diagnostic measures to coaching and mentoring junior staff
• Provide significant input to Product Management on implementation specifications and production testing
• Review reports and make recommendations for needed model refits/enhancements
• Keep abreast of business trends/product needs
• Other duties as assigned by the Management

Requirements:

• One year of professional experience building predictive and descriptive statistical models
• Graduate degree (M.S., Ph.D. preferred) in a quantitative discipline
• Extensive experience working with large datasets
• Experience with complex predictive Time Series models and methodologies
• Knowledge, experience, and expertise in diverse statistical and data mining techniques (e.g. - GLM/Regression, Boosting, Random Forest, Trees, Clustering, PCA, SVM, Neural Networks, Deep Learning, etc)
• Demonstrated proficiency with statistical packages in Spark ML-Lib, Python, R, or SAS
• Understanding of RDBMS and interactive SQL programming skills
• Ability to program in Python, Scala, R, or SAS
• Experience with Big Data technologies like Hadoop, Spark, Hive, NoSQL, etc., and Cloud technologies (AWS, Azure, etc.)