As Principal Data Scientist you will lead the Energy division data science team. You will be responsible for design and build predictive and cognitive algorithms for optimizing the performance and control of distributed energy resources (DER), develop self-learning systems that can predict and autocorrect based on data, develop predictive control models, optimization and machine learning, aimed at design, automation and optimal performance of large-scale, real-time dynamic systems, gather & analyze data, devising data science solutions for high-performance real-time models, and propose innovative algorithms and pursue patents where appropriate.
You will also work with engineering teams to incorporate solutions and create intuitive UX stories. Partner with data engineers on data quality assessment, cleansing, and analytics, research and evaluate emerging technology and market trends to assist in project development and operational support for the Energy team, contribute to the development of software and data delivery platforms that are service-oriented and reusable, and creat reports and other artifacts to document your work and outcomes. Communicating methods, findings, and hypotheses with stakeholders.
- Master's degree in Computer Science, Statistics, Machine Learning, Mathematics, or any other related quantitative field.
- 10+ years of hands-on experience in a data science position, working as a Senior Data Scientist.
- 5+ years of people management experience leading a data sciences team.
- Knowledge and implementation experience of Hamiltonian and Lagrangian mathematics.
- Strong expertise in power system modeling, power system operation, power system optimization, integration of distributed energy resources (DER), energy management system (EMS), and supervisory control and data acquisition (SCADA).
- Have experience in Machine Learning/AI techniques including Deep learning (RNN, CNN, GAN, etc), Support Vector Machines; Regularization Techniques; Boosting, Random Forests, Ensemble Methods, image/video/audio processing, Bayesian, and time series modeling.
- Have good implementation experience with R, Python, Perl, Ruby, Scala, Apache Spark, Storm, SAS, and the ability to work with a variety of Deep learning frameworks including TensorFlow, Keras, Caffe, CNTK, etc.
- Have hands-on skills in sourcing, manipulating, and analyzing large volumes of data including SQL and NoSQL databases.
- Have proven experience in using well-established supervised and unsupervised machine learning methods for large industry-strength data analysis problems.
- Excellent communication (written / verbal).