Senior Data Scientist Job Listing at Nextracker in Sorocaba, SP (Job ID NX-549)

Description

Job Description:

At Nextracker, we are leading in the energy transition, providing the most comprehensive portfolio of intelligent solar tracker and control software solutions for solar power plants, as well as strategic services to capture the full value of solar power plants for our customers. Our talented worldwide teams are transforming PV plant performance every day with smart technology, data monitoring and analysis services.

As a company driving the clean energy transition, sustainability is not just a word. It's a core part of our business and our operations. Our sustainability efforts are based on five cornerstones: People, Community, Environment, Innovation, and Integrity. We are creative, collaborative and passionate problem-solvers from diverse backgrounds, driven by our shared mission to provide smart solar and software solutions for our customers and to mitigate climate change for future generations. Make your mark with Nextracker.

The Senior Data Scientist will be based in the Brazil.  The Senior Data Scientist will work with the Nextracker team to analyze data in-field operations of Nextracker systems that will improve the Nextracker product portfolio and support customer success. They will work with a diverse and dedicated team of computer scientists and engineers to grow Nextracker's reach world-wide.

We are looking for someone who demonstrates:

• Passionate drive to innovate and create
• Integrity to the core
• Enthusiastic customer focus
• Consistent interactive teamwork
• Desire for continuous improvement and top performance

Here is a glimpse of what you'll do…

• Lead research into operational metrics, data signatures, and all aspects of field operational time series data analysis for a giant fleet of solar trackers
• Implement algorithms on scalable data science architecture in the cloud, such as DataBricks, to analyze various metrics entire operational fleet for a full characterization of the installed base
• Implement algorithms in Python (or similar) codes, test, validate, and support efforts to integrate new analytic technologies into existing monitoring and data systems
• Develop algorithms to detect tracker health problems, both electrical and mechanical, and validate against ground truth internally or in collaboration with customers
• Develop algorithms to predict future tracker health problems using a deep understanding of available data measurement points
• Design diagnostic systems and algorithms to identify root causes of operational issues
• Design and implement prototype reports, data exports, visualizations, and other ways of communicating results that cleanly and crisply convey appropriate information internally within Nextracker as well as customer-facing views
• Design relevant field experiments and collaborate cross-functionally to execute them and collect validation data
• Support definition of new customer-facing product features, reports, and analytic systems that can be monetized based on customer value
• Support ad-hoc data science activities related to field performance
  • Interpret data, analyze results using statistical techniques; develop and provide ongoing reports
  • Optimize statistical efficiency and quality throughout, and establish appropriate process and business practices to ensure efficient execution
  • Clean, filter, and manage large sets of data; identify data quality/integrity improvements and ensure they are properly addressed
  • Help troubleshoot PV equipment, performance, or operational issues
• Mentor junior staff and support international data science and solar performance engineering teams with essential knowledge and expertise on best practices in solar performance, machine learning, data science, visualization, and clear communication of results and methods

Here is some of what you'll need (required):

• Master's Degree in Mathematics, Engineering, Computer Science, Information Management, Statistics, or related discipline
• Minimum 7 years of data science, performance engineering or analytics experience, working with large time series data sets
• Minimum 2 years solar domain experience, preferably relating to the performance, design, operations and maintenance, and modeling of utility-scale solar power plants
• Strong analytical skills with the ability to collect, organize, analyze, and disseminate significant amounts of information with very strong attention to detail and accuracy
• Experience working with time series datasets from operating power plants including data cleaning, validation, and understanding of key relationships between various physical quantities represented in the data
• Experience accessing and handling large data sets, APIs, and ML analysis tools in Python
• Knowledge of statistics, and experience using statistical packages for analyzing datasets
• Ability to identify, analyze, and interpret trends or patterns in complex data sets
• Technical expertise regarding data models, data mining and segmentation techniques
• Feature selection, regression, comparison and tuning of machine learning methods with time series data.
• Familiarity with operational aspects of electro-mechanical systems, failure modes, equipment health evaluation and tracking methods, such as rain flow counting, near neighbors comparison, expected performance modeling and deviation detection, change point detection, filtering
• Familiarity with uncertainty propagation and related statistical analysis in determining confidence in results
• Excellent communication and presentation skills, thoroughness in investigations, and ability to juggle several in-progress projects and related schedules and milestones
• Ability to develop, prioritize, and drive initiatives

Additional qualifications (preferred):

• Ph.D. is a plus
• Knowledge of and experience with scalable data science platforms, such as DataBricks on Azure
• Knowledge of and experience with reporting packages, such as Power BI
• Familiarity with performance engineering tools including PVsyst, PVLIB Python, NREL SAM, and other PV software, models, and tools
• Solar industry specific experience regarding solar power plant operational performance, with understanding of system design, SCADA/DAS control and monitoring systems, remote communications, and common key performance indicators such as performance ratio, availability, production actual to budget, and related metrics
• Foundational understanding of basic quantities and processes in solar performance including solar resource, sun position, irradiance, transposition models, analysis techniques, module technologies, inverter behaviors, and related topics

Nextracker is an Equal Opportunity Employer and employment selection decisions are based on merit, qualifications, and abilities.  Nextracker does not discriminate in employment opportunities or practices on the basis of: age, race, religion, color, sex, national origin, marital status, sexual orientation, gender identity, veteran status, disability, pregnancy status or any other status protected by law.

Nextracker provides reasonable accommodation so that qualified applicants with a disability may participate in the selection process. Please advise us of any accommodations you request in order to express interest in a position by e-mailing: accesibility@flextronics.com. Please state your request for assistance in your message. Only reasonable accommodation requests related to applying for a specific position within NX will be reviewed at the e-mail address. Thank you for considering a career with Nextracker.

At Nextracker, we are leading in the energy transition, providing the most comprehensive portfolio of intelligent solar tracker and software solutions for solar power plants, as well as strategic services to capture the full value of solar power plants for our customers. Our talented worldwide teams are transforming PV plant performance every day with smart technology, data monitoring and analysis services.

For us at Nextracker, sustainability is not just a word. It's a core part of our business, values and our operations. Our sustainability efforts are based on five cornerstones: People, Community, Environment, Innovation, and Integrity. We are creative, collaborative and passionate problem-solvers from diverse backgrounds, driven by our shared mission to provide smart solar and software solutions for our customers and to mitigate climate change for future generations.