Computational Scientist Differentiable Physics
Periodic LabsVisit Periodic Labs website
AI research and deployment company building AI scientists and autonomous laboratories for physical-science discovery.
Menlo Park, United States
About Periodic Labs
Periodic Labs develops specialized AI models and high-throughput autonomous labs that run and analyze physical experiments, initially for materials discovery including superconductors, magnets, and semiconductor applications.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build and extend differentiable continuum-simulation solvers, implement and diagnose numerical methods, and combine simulation with deep learning. You will use automatic differentiation and accelerators, validate models, and create datasets and evaluations for scientific automation.
Requirements
- Continuum physics
- Fluid dynamics
- Governing equation
- Solver development
- PDE solver
- Numerical method
- Differentiable simulation
- Deep learning
- Python
- JAX or PyTorch or Julia or C++
Responsibilities
- Build and extend differentiable continuum-simulation solvers
- Implement numerical methods and diagnose modeling failures
- Combine simulation with deep learning
- Use automatic differentiation and accelerators for scalable simulations
- Validate models against experiments benchmarks or high-fidelity simulations
- Create datasets and evaluations for scientific automation
Benefits
- Visa sponsorship