We are looking for a Data Scientist intern who will work with the team to develop algorithms packages to deliver data-analytical services and products for our clients on top of the EnOS platform. The ideal candidate is adept at using a variety of ML/AI models, from traditional statistical learning models to deep-learning models, to address various data-driven requirements. They should have some experience in data exploration, building/implementing models, and delivering modeling results to stakeholders. They need to demonstrate their data-based insights. They must be comfortable working with a wide range of stakeholders and functional teams. The ideal candidate would have a passion for investigating solutions and working with stakeholders to improve algorithms results. 

Major Responsibilities 

1. Work with team and stakeholders to implement data-analytical packages for clients in multiple domains; 
2. Perform data exploration in depth and design/implement novel algorithms to address data analytical challenges; 
3. Work closely with other platform teams to deliver integrated products or solutions 

Qualifications 

1. Excellent understanding of general machine-learning techniques and popular models (linear regression, SVM, XGBoost/LightGBM, etc.), and basic deep-learning models. 
2. Experience with development tools like Python, NumPy/Pandas, Scikit-learn, and one deep-learning framework (Tensorflow / Keras / PyTorch) 
3. Experience with data exploration tools and data visualization tools, such as matplotlib, Echarts, etc. 
4. Good to have experience with SQL/NoSQL databases 
5. Excellent written and verbal communication skills for coordinating across teams. 

Capstone project description  

Predictive Maintenance (IoT) 

• Analyze sensors data sets and extract key features 
• Build models for outlier detection/health status detection, etc 

• Deploy ML model in AI platform and analyze model performance 

Building Energy Analysis 

• Analyze building energy data to understand the electricity usage in different assets 
• Provide insight to explore the abnormity energy usage cases 

• Design and build machine learning models to forecast the energy usage 
• Design and build machine learning models to forecast abnormal energy usage cases 
• Iteratively to tune and improve model performance 

Qualifications 

1. Excellent understanding of general machine-learning techniques and popular models (linear regression, SVM, XGBoost/LightGBM, etc.), and basic deep-learning models. 
2. Experience with development tools like Python, NumPy/Pandas, Scikit-learn, and one deep-learning framework (Tensorflow / Keras / PyTorch) 
3. Experience with data exploration tools and data visualization tools, such as matplotlib, Echarts, etc. 
4. Good to have experience with SQL/NoSQL databases 
5. Excellent written and verbal communication skills for coordinating across teams.