Postdoc: Climate & Power Systems (ML/RL)

University of Virginia; Charlottesville (VA); On-site; USD 64,000 - 78,000; Full time

Job summary

The University of Virginia’s Environmental Institute invites applications for a Postdoctoral Research Associate to advance a Climate and Power Systems project. The role entails interdisciplinary collaboration among faculty and researchers focusing on ML, optimization, and resilient infrastructure to address climate-driven energy system challenges.

The selected candidate will help develop a robust multi-agent reinforcement learning framework for joint expansion, transition, and resilience

Qualifications

• Doctoral degree completed or anticipated by start of the appointment.
• Strong background in power systems, ML, and optimization.
• Experience with reinforcement learning or multi-agent systems.
• Excellent written and oral communication; dissemination to academic and industry audiences.
• Willingness to collaborate with industry and stakeholders.
• Leadership and initiative to drive project direction.

Responsibilities

• Develop a robust MARL framework for expansion, transition, and resilience planning.
• Model power system complexities under climate-driven uncertainties.
• Collaborate with interdisciplinary team and utility providers.
• Disseminate findings through conferences and journal articles.
• Contribute to project planning and reporting.

Skills

Interdisciplinary research

Power systems

Machine learning

Optimization

Reinforcement learning

Multi-agent systems

Communication skills

Leadership

Industry collaboration

Education

PhD or doctoral degree

Job description

The University of Virginia’s Environmental Institute invites applications for a Postdoctoral Research Associate to advance a Climate and Power Systems project. The role entails interdisciplinary collaboration among faculty and researchers focusing on ML, optimization, and resilient infrastructure to address climate-driven energy system challenges.

The selected candidate will help develop a robust multi-agent reinforcement learning framework for joint expansion, transition, and resilience