Postdoctoral Appointee - Scientific Machine Learning for Surrogate Modeling and Power Grid Dynamics
Argonne National Laboratory is seeking a Postdoctoral Appointee to conduct cutting-edge research in scientific machine learning, focusing on developing machine learning-based surrogates and emulators for power grid dynamics. The role involves creating advanced probabilistic models for dynamical systems, integrating them into large-scale optimization frameworks to enhance power grid operations.
Responsibilities
- Conduct cutting-edge research in scientific machine learning
- Develop machine learning-based surrogates and emulators for the dynamics of power grids
- Create advanced probabilistic models that capture the complex behaviors of dynamical systems
- Integrate models into large-scale optimization frameworks to enhance the efficiency and reliability of power grid operations
- Ensure trustworthy computations and scalability on the DOE’s leadership computing facilities
- Develop robust, scalable solutions that are computationally efficient and maintain accuracy within operational constraints
Skills
- Ph.D. (completed within the past 0-5 years) in computer science, electrical engineering, applied mathematics, or a related field
- Strong proficiency in Python, with additional experience in C, C++, or similar languages
- Demonstrated expertise in machine learning, especially in the context of dynamical systems modeled by differential-algebraic equations
- Experience with high-performance computing and the ability to scale models using distributed computing environments
- Excellent oral and written communication skills for effective collaboration across multiple teams
- Commitment to embodying the core values of impact, safety, respect, and teamwork in all endeavors
- Extensive experience with power grid models and large-scale optimization problems
- Familiarity with developing machine learning surrogates and emulators for dynamical systems
- Proficiency in managing large datasets and training with GPU-enabled computing resources
- Expertise in numerical optimization and familiarity with ML frameworks such as PyTorch, Jax, or TensorFlow
- A strong foundation in statistical methods, probability theory, or uncertainty quantification is highly advantageous
Benefits
- Comprehensive benefits are part of the total rewards package
Company Overview