Many of the challenges of renewable energy revolve around different kinds of time series forecasting. How much energy will a solar plant produce during a given window of time? How much will a particular consumer require? How can we resolve discrepancies between the two in a cost-effective way?
As part of our data science team you will research cutting edge, scalable machine-learning solutions to challenges like these, with a strong focus on driving improvements directly to production systems. As an early team member you will have significant opportunities to design key parts of our solutions, and to hold leadership or domain-expert roles as the company grows.
The ideal candidate for this role is an experienced data scientist who can blend high-quality science with strong awareness of what drives effective production solutions:
- 3+ years of data science/applied machine learning experience, with strong foundation in statistics
- good skills in Python
- experienced with both short- and long-term time series forecasting
- strong problem-solving skills to help refine problem statements and figure out how to solve them with available data
- good hands-on skills in feature engineering and hyperparameter optimization (understanding the science, not just treating models as magic black boxes)
- capable of crafting reproducible analyses with a strong focus on reliable backtesting that can be applied to explore multiple different solutions
- able to write clean and tested code that can be maintained by other software engineers
- able to clearly summarize and communicate data analysis assumptions and results
- able to craft effective data pipelines to transform your analyses from offline to real-time production systems
- able to design and implement metrics and tools to support effective assessment of models both for local testing and production systems
- interested in helping to create a new data science development platform
- a keen eye for new trends and techniques, and the creative energy to explore and apply them effectively
- the desire to advance data science, not just apply it
- self-driven and strongly motivated to explore and implement new solutions without supervision
- smart but humble, with a focus on action
Bonus points for:
- a degree in computer science, statistics, or a related field
- experience with other programming languages
- experience or familiarity with data engineering
- experience with Linux devops
- experience with continuous integration and continuous development (CI/CD)
- understanding and experience with distributed computing
- understanding and experience with IoT/edge development
- experience with forecasting challenges in electricity production or electricity trading