• US Citizen

• Green Card

• Corp-Corp

• Consulting/Contract

• UG :- - Not Required

• PG :- - Not Required

• No of position :- ( 1 )

• Post :- 4th Jun 2022

D• Proficiency with Python or R, SQL and familiarity with working in big data environments (2 years minimum)
• At least 3+ years of experience of deploying machine learning models and frameworks in production
• At least 5 years of experience with:
o Experiences in both Supervised and Unsupervised machine learning models (Regressions, Gradient Boosted methods, SVMs, Random Forests, Clustering)
o Familiar with python packages such as Pandas, SkLearn, Numpy etc
o Time Series Analysis (ARIMA, SARIMAX, MA)
o Deep learning (CNN, RNN, LSTM) and framework library (e.g., Keras, TensorFlow, PyTorch) and Graph Neural Networks
o End to end machine learning lifecycle experience including feature engineering, model building, model versioning, evaluation and hypothesis testing.
• At least 3 years of experience with 
o Cloud computing platforms such as AWS, Azure (preferably AWS)
o Containerization and orchestration technologies such as Docker and Kubernetes.
o Standard concepts and technologies used in CI/CD build and deployment pipelines. 
• At least 2 years of experience in distributed computing frameworks such as Spark or Pyspark is desirable.

Summary
The Client Power Digital Core organization is leading Client's efforts to design, develop, deliver and maintain a global energy management platform that unlocks value across Client's Power business. Client Power Digital Core aims to enable Client's efforts to harness the potential in its vast fleet of customers, energy assets, and power trading capabilities to deliver value across the energy industry value chain.
As a full stack data scientist, you will get to apply your knowledge in statistics, time series analysis, and dynamical systems, work with the latest machine learning models, and build predictive models for energy consumption, energy generation, and energy price, and make an impact by helping Power Digital Core clients to make better, safer, more sustainable decisions which yields to cleaner and more sustainable world.
WHAT YOU'LL DO:
You will work with a team of data engineers and scientists who use data and apply cutting statistical machine learning models to build forecasting models for different energy markets. The entire Data team works collaboratively and is a strong partner for teams across the company. You will get to meet and learn from diverse and talented colleagues. Specific responsibilities include:
• Analyze energy time series and summarize the statistical properties of energy signals
• Build predictive models and forecast signals for day-ahead and real-time markets
• Evaluate the performance and compare the results with existing models
• Deploy the best model and document the result of this research

Business Skills
• Excellent verbal, written, and interpersonal communication skills
• Strong understanding of the product development lifecycles
• Strong understanding of software development, testing and integration methodologies
• Personal effectiveness/credibility
• Strong problem solving and analysis skills

Technical Skills
• Proficiency with Python or R, SQL and familiarity with working in big data environments (2 years minimum)
• At least 3+ years of experience of deploying machine learning models and frameworks in production
• At least 5 years of experience with:
o Experiences in both Supervised and Unsupervised machine learning models (Regressions, Gradient Boosted methods, SVMs, Random Forests, Clustering)
o Familiar with python packages such as Pandas, SkLearn, Numpy etc
o Time Series Analysis (ARIMA, SARIMAX, MA)
o Deep learning (CNN, RNN, LSTM) and framework library (e.g., Keras, TensorFlow, PyTorch) and Graph Neural Networks
o End to end machine learning lifecycle experience including feature engineering, model building, model versioning, evaluation and hypothesis testing.
• At least 3 years of experience with 
o Cloud computing platforms such as AWS, Azure (preferably AWS)
o Containerization and orchestration technologies such as Docker and Kubernetes.
o Standard concepts and technologies used in CI/CD build and deployment pipelines. 
• At least 2 years of experience in distributed computing frameworks such as Spark or Pyspark is desirable.