National Renewable Energy Laboratory

Artificial Intelligence

• Contribute to the development of software to execute power characterization experiments of AI LLM workloads under different parameter assumptions i.e. sensitivity analysis
• Performing computational experiments, running batch experiments on NLR HPC using SLURM
• Analyzing results capturing trends and tradeoffs between parameter configurations
• Coordinating data exchange to inform other team members’ efforts
• Contribute to writing and presenting reports and conference proceedings related to characterization tests

Graduate Intern – AI Data Center Workloads Characterization & Simulation

Machine Learning Engineer

• looking for a year-round intern (summer intern is also acceptable)
• work on projects developing learning-based analytics
• cyber-attack-resilient control strategies and optimizations for power distribution systems
• conducting literature review
• identifying gaps and summarizing new research opportunities
• conduct research work independently
• collaborate with project PI and other researchers from the project team

Graduate PhD Student – Machine Learning Applications for Cyber-Physical Power System Operations Intern

Software Engineer

• Develop and implement novel mathematical optimization models (e.g., stochastic programming, robust optimization, mixed-integer linear programming) for medium-term grid planning.
• Design and code efficient algorithms for large-scale optimization problems using the Julia programming language and packages such as JuMP.jl.
• Collaborate with a multidisciplinary team of engineers, computer scientists, and data scientists to put research insights into open-source software products.
• Publish research findings in leading academic journals and present at major international conferences.
• Contribute to the development of the open-source power systems modeling software Sienna.

Postdoctoral Researcher – Model Engineering

• Innovate and Optimize: Build best-in-class models for inverter-level and plant-level solar forecasting with calibrated uncertainty, using RNN, diffusion models, and graph models
• Implement and Impact: Bring your algorithms to life for industry partners, making tangible improvements in solar forecasting
• Lead and Collaborate: Manage our project GitHub repository for experiment tracking and code versioning, ensuring seamless collaboration with partners and code excellence
• Share Your Discoveries: Present your groundbreaking results and key findings at workshops, conferences, and in high-quality journals, positioning yourself as a thought leader in the field

Graduate Intern – AI Data Center Workloads Characterization & Simulation

Graduate PhD Student – Machine Learning Applications for Cyber-Physical Power System Operations Intern

Postdoctoral Researcher – Model Engineering

Graduate Intern – Machine Learning, Solar Forecasting