Energy Analysis Research Fellow

Position: Energy Analysis Research Fellow

Duration: 2 years and possible extension

Location: Remote

Position Type: Contract

Travel possibility: 10% possible travel – once/ twice in a quarter to various client location

Work hours: 40 hours per week

Job Description:

Client is hiring an Energy Analysis Research Fellow. This is your chance to be at the forefront of energy innovation, working alongside a dynamic, multidisciplinary team of experts from client and NREL. As a Research Fellow, you will dive into a groundbreaking project (DOE News), developing and implementing cutting-edge AI algorithms for energy applications. Your primary mission will be to leverage your expertise in artificial intelligence and statistics to revolutionize energy forecasting. Your deep knowledge of renewable energy, weather/climate modeling, and statistical/machine learning will be the driving force behind your success in this role.

Desired Skills:

• Hands-on experience in energy/time series forecasting, such as participating in energy forecasting competitions.
• Experience in weather/climate data analysis and numerical weather predictions.
• A solid background in power and energy systems.
• Education Requirements: Doctorates
• Certifications needed: NA

Key Responsibilities:

• Innovate and Optimize: Develop state-of-the-art machine learning algorithms to select, combine, and optimize electric load, wind, and solar forecast time series scenarios.
• Master Uncertainty: Create sophisticated machine/statistical learning algorithms for uncertainty quantification.
• Implement and Impact: Bring your algorithms to life within the client’s system, making a tangible impact on energy forecasting.
• Lead and Collaborate: Manage our project GitHub repository, ensuring seamless collaboration and code excellence.
• Share Your Discoveries: Present your ground breaking results and key findings at workshops, conferences, and in high-quality journals, positioning yourself as a thought leader in the field.

Essential Experience and Education:

• A current PhD candidate in Computer Science, Computer Engineering, EE, Applied Math, Data Science, Statistics, or a related analytical domain.
• Expertise in Python and its related libraries, such as Tensorflow, Keras, Pytorch, Open AI Gym.
• Proven experience in timeseries forecasting, reinforcement learning, and scenario generation.
• A comprehensive understanding of uncertainty quantification and Bayesian theory.
• A track record of publishing high-quality research papers.

Desirable Qualifications:

• Hands-on experience in energy/time series forecasting, such as participating in energy forecasting competitions.
• Experience in weather/climate data analysis and numerical weather predictions.