Arena is building the world's first AI industrial engineer, Atlas, to solve complex hardware and manufacturing challenges by understanding physical systems and physics, aiming to redefine the future of hardware engineering.
Requirements
- Proven expertise building and training large foundation models
- Experience with FNO and/or Neural Operators
- Understanding of EM solvers (FEM/FDTD/MoM)
- Strong Python, PyTorch/JAX, C/C++ for bindings
- Proven record of physics-constrained ML or scientific simulation deployment
- Prior work on passivity/causality enforcement in learned models
- Familiar with PDN, high-speed channel design, and EMI compliance testing
Responsibilities
- Design FNO/AFNO/Deformation-FNO/U-FNO multiscale operator architectures with embedded physical constraints
- Implement causality/passivity enforcement and uncertainty calibration
- Specify coverage targets for proprietary training data corpora
- Work with Arena’s Platform Engineering team to orchestrate solver farms and synthetic generation
- Work with Arena Electrical Engineers to define a set of requirements and interface for physically-generated training data via hardware-in-the-loop test campaigns
- Develop sim-to-real calibration using for example VNA/near-field/BER measurements
- Build automated accuracy and constraint eval suite
Other
- PhD or equivalent research track in Electrical Engineering, Applied Physics, Computer Science, or Applied Math
- Own releases and reporting
- Profile inference latency and throughput
- Author design docs, experiments, and technical reports
- Relocation support provided (NYC or SF)
