Research Scientist, Computational EM

Arena Physica is on a mission to accelerate hardware innovation that powers human progress. 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 ~$90M 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. What we do At Arena Physica, we're building electromagnetic superintelligence. 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, Anduril, and Bausch & Lomb, for applications across R&D, integration testing, production assembly, and field repair. About the role As a Research Scientist, Computational EM, you will own the mathematical foundation that allows us to turbocharge our data factory and informs our machine learning approaches as we expand our EM foundation model capabilities. You will optimize our solvers for speed and expanded physical fidelity and focus on translating mathematical solutions to the underlying PDEs to novel machine learning approaches and inform inductive biases that shape how our models learn EM physics. You'll work directly with our existing and fast-growing research team and partner with senior leadership on the research roadmap. This is a truly unique opportunity at the intersection of a renewed industrial and political focus on hardware and the emergence of AI for Physics. At Arena Physica you will work with diverse expert teams across Software, Hardware, and ML. If you are ambitious, drawn to big bets, and truly excited about transforming how we apply physics to hardware development this role is for you. How you will contribute Optimize and Extend Our Solvers: Profile, debug, and optimize core EM solvers across performance, accuracy, and conditioning — improve throughput on the simulation campaigns that train the foundation model. Extend solver capability to include additional physical phenomena (frequency-dependent materials, lossy media, dispersive substrates, nonlinear effects, broadband regimes) so our training corpus covers the geometries and conditions production use cases require. Inform Model Architecture: Bring mathematical judgment from solving underlying PDEs into architecture decisions: basis function choices, structure-preserving discretizations (DEC, mimetic methods), conservation enforcement, well-posedness, scale invariance. Partner with the ML research team on inductive biases that respect the PDE structure of Maxwell's equations. Derive and implement downstream observable EM characteristics from predicted fields (e.g., far-field, S-parameters, surface currents) and define clear relationships between solutions of different boundary conditions and excitation modes and locations. Translate Research into Atlas Deployments: Partner with the Atlas product and platform engineering teams to land research artifacts in production deployments across our customer base. Define accuracy, conditioning, and performance requirements that production EM use cases need; close the loop from production data back into research direction. Author Research Publications: Author papers at top venues (IEEE TAP, ACES, IMS, NeurIPS, ICML, ICLR) that establish Arena Physica's research footprint and externally validate the foundation-model approach. Own at least one substantive publication per year as first author. Drive External Collaborations: Develop and support research collaborations with academic labs and industry partners on computational EM and ML-for-PDE problems; represent Arena Physica externally at conferences, workshops, and customer engagements. You have PhD in Applied Mathematics, Computational Electromagnetics, Applied Physics, or Electrical Engineering. Direct EM specialization preferred; closely related solver-heavy fields (e.g., CFD, computational mechanics, computational acoustics) considered. A track record of original, published, mathematically rigorous work on PDE solvers — new formulations, discretizations, conditioning analyses, or scaling work at a fundamental level. Not just running solvers but advancing them. Deep familiarity with EM solver families and their mathematical foundations: FEM, FDTD, MoM, BEM, eigenmode analysis, Green's functions, integral-equation methods, Krylov / multigrid / preconditioned solvers. Strong intuition for the physical meaning of solver design choices — basis functions, mesh strategies, boundary condition handling, scale invariance, conservation laws. Hands‑on experience contributing to a real codebase — ideally production code that runs at scale. Proficiency in scientific computing across C / C++ / Fortran and Python; comfort with sparse linear algebra, BLAS / LAPACK, MPI, and the optimization patterns that make large EM simulations run fast. A clear point of view on how solver mathematics should inform ML architecture choices for EM — basis function choice, inductive biases, structure-preserving discretizations. Preferred: Prior ML / neural-operator work, particularly applied to PDEs (PINN, Fourier neural operator family, Transolver-class architectures, DeepONet). Preferred: Contributions to open-source EM or PDE solvers (Palace, MEEP, OpenEMS, FEniCS, deal.II, comparable). Preferred: Experience with HPC ecosystems (Slurm, AWS Batch, EFA, MPI, message-passing workloads at scale). Benefits & Perks Include 100% of the monthly premiums covered with Aetna medical vision, and dental insurance for you and your dependents. 401(k) Retirement Plan. Unlimited PTO. Lunch every day from local restaurants via Sharebite. Relocation support provided. #J-18808-Ljbffr Arena Physica