Principal Research Scientist, Electromagnetism

Location: New York or San Francisco

Department: Applied Research

Who we are:

Arena Physica is building electromagnetic superintelligence. Our name is inspired by Theodore Roosevelt's 'Citizenship in a Republic' speech. To us, entering the Arena means committing fully and accepting the risk of failure in pursuit of an audacious, worthy cause. We believe the future belongs to those brave enough to build it.

Our team of 50 combines AI engineering and applied physics expertise with deep experience in enterprise deployments. We're headquartered in NYC with presences in San Francisco and Los Angeles, backed by $62M from Initialized, Founders Fund, Goldcrest Capital, Fifth Down Capital, and Shield Capital.

If you're ready to do the most important work of your career, join us in the Arena Physica.

What we do:

At Arena, we're building foundational intelligence for modern hardware. Our AI platform Atlas operationalizes physics-grounded intelligence to verify, debug, and optimize hardware across its lifecycle. Atlas is already trusted globally by the world's most advanced hardware companies, including AMD and Bausch & Lomb, for applications across R&D, integration testing, production assembly, and field repair.

About the role:

As a Principal Research Scientist, Electromagnetism, you will lead the architecture, training, and validation of our electromagnetic foundation model, bridging numerically solved physics equations, neural operators, and product-grade simulation.

How you will contribute:

• Model Architecture Research
  • Design FNO/AFNO/Deformation-FNO/U-FNO multiscale operator architectures with embedded physical constraints
  • Implement causality/passivity enforcement and uncertainty calibration
• Proprietary Training Data Corpora
  • Specify coverage targets
  • 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
• Evaluation & Validation
  • Build automated accuracy and constraint eval suite
  • Own releases and reporting
• Optimization & Performance
  • Profile inference latency and throughput
• Leadership & Documentation
  • Author design docs, experiments, and technical reports

You have:

• PhD or equivalent research track in Electrical Engineering, Applied Physics, Computer Science, or Applied Math
• 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
• [Preferred] Prior work on passivity/causality enforcement in learned models
• [Preferred] Familiar with PDN, high-speed channel design, and EMI compliance testing
• [Preferred] Experience and familiarity with high performance principles (e.g. Slurm for scheduling, message passing workloads, etc.), and cloud service provider HPC ecosystems (e.g. AWS Batch, Elastic Fabric Adapter, etc.)

Benefits & Perks Include:

• 100% of the monthly premium for Aetna medical insurance, plus vision and dental coverage
• 401(k) Retirement Plan
• Unlimited PTO
• Lunch every day from local restaurants via Sharebite
• Relocation support provided (NYC or SF)

The base salary range for this position is $250,000 - $350,000 yr. However, base pay offered may vary depending on job-related knowledge, skills, and experience. In addition to base salary, we also offer competitive equity and benefits packages.