- Master of Science or PhD Degree in Engineering, Computer Science, Physics or any other relevant discipline, or bachelor's degree with equivalent relevant working experience.
- 6-10 years of working experience with Data Science techniques and frameworks in a relevant domain, including data preparation (cleaning, discretization, normalization, sampling), data exploration (correlation, analysis, plotting) and modeling (supervised/unsupervised methods) which includes: -
- Knowledge of Machine learning techniques including data mining, statistical analysis, deep learning, and anomaly detection.
- Conducting analysis to derive strategic insights from vast condition monitoring datasets including SCADA (Supervisory Control and Data Acquisition Data).
- Domain knowledge and/or work experience in Predictive Maintenance/Condition Monitoring of machines, vibration data analysis, Signal Processing, Reliability Engineering of wind turbines or similar would be a great advantage.
- Solid theoretical background in Statistical modeling, Predictive analytics, Probabilistic forecasting, Time Series and Machine Learning.
- Experience with End-to-End data science model lifecycle in Product development context: from analysis/research stages, model design, implementation, deployment to production environments and monitoring.
- Experience in designing numerical solutions to real-world business problems, with the primary emphasis on business value.
- Familiarity with Agile Development Methodologies and Tools.
- Excellent verbal and written communication.
- Strong ability to provide technical guidance, share expertise and provide mentorship to team members.
- Self-driven and requiring minimal inputs with basic tasks assigned.
- Ability to breakdown larger tasks assigned to self and manage effective tracking of the same.
- Understand cross functional team dependencies and call them out effectively.
- Preferred Experience in the Renewable Energy Domain.
- Demonstrated ability to effectively communicate with non-technical stakeholders such as Product Owners and Product Directors.
Technology Skills Required:
- 6+ years of Demonstrable fluency in Data Science frameworks and tools in Python: Pandas, SciPy, Scikit-learn, TensorFlow, Matplotlib, Plotly.
- 6+ years' experience in building Data Science & Machine Learning Tools.
- 6+ years' experience with Big Data frameworks on cloud environments: Spark, AWS (Amazon Web Services) Cloud Services.
- 6+ years’ experience in Version control using GitHub/Bitbucket or similar.
- 4+ years’ experience in EDA (Exploratory Data Analysis)/EDA Data Transformation/Feature Selection.
- 4+ years’ experience in Developing Classification Models/Hyper Parameter Tuning.
- 4+ years’ experience in Supervised/Unsupervised Learning
- 4+ years’ experience in Model Evaluation using KPIs (Key Performance Indicators) - RMSE (Root Mean Square Error)/MAE (Mean Absolute Error)