Master's or Ph.D. in Computer Science, Mathematics, EE, Physics, or a related quantitative field focusing on Scientific Machine Learning (SciML).
At least 4 years of expert experience with PyTorch or JAX deep learning frameworks.
Hands-on experience building and training Physics-Informed Neural Networks (PINNs), DeepONets, or Fourier Neural Operators (FNOs).
Strong mathematical background in partial differential equations (PDEs), vector calculus, and numerical optimization algorithms.
Proficient in Python libraries for manipulating spatial or geometric datasets, such as NumPy, SciPy, Shapely, or Open3D.
Responsibilities
Design and train advanced deep learning models, focusing on PINNs, FNOs, and Neural Operators to resolve key equations related to physics.
Develop high-performance data pipelines to convert various PCB file formats into tensor grids or graph embeddings.
Implement Differentiable Physics Calibration pipelines to integrate lab measurement data for manufacturing parameter adjustments.
Collaborate on multi-modal architecture integration, linking GNNs or LLMs with spatial physics engines.
Optimize training and inference to achieve real-time execution of physics predictions under 100 milliseconds.
Benefits
Opportunity to work at the cutting edge of Scientific Machine Learning.
Collaborative environment that fosters innovation in deep learning and physics.
Access to state-of-the-art computational resources and GPU clusters.
Continuous learning opportunities through hands-on projects and advanced technologies.
Full Job Description
Core Responsibilities
Architect Physics Foundation Models: Design and train deep learning models-specifically PINNs, FNOs, and Neural Operators-optimized to solve Maxwell's equations, Helmholtz equations, and heat equations directly within the neural loss function.
Build the ECAD Data Pipeline: Develop high-performance asset pipelines to convert geometric, discrete, and multi-layer PCB files (ODB++, IPC-2581, STEP, Gerber) into continuous tensor grids, signed distance fields (SDFs), or graph embeddings.
Close the Simulation-to-Reality (Sim2Real) Gap: Implement Differentiable Physics Calibration pipelines to ingest physical lab measurements (VNA Touchstone files, TDR traces, near-field EMI scans) to fine-tune latent material and manufacturing parameters.
Multi-Modal Architecture Integration: Collaborate on connecting upstream Graph Neural Networks (GNNs) or LLMs mapping schematic topologies to downstream spatial physics engines.
Optimize for Real-Time Execution: Optimize training and inference pipelines on GPU clusters to ensure forward-pass physics predictions can execute in sub-100 millisecond timeframes, enabling real-time feedback loops for layout designers.
Required Technical Skills & Qualifications
Education: Master's or Ph.D. in Computer Science, Mathematics, EE, Physics, or a related quantitative field with a focus on Scientific Machine Learning (SciML).
Deep Learning Frameworks: 4+ years of expert-level experience with PyTorch or JAX.
SciML Expertise: Direct, hands-on experience building and training PINNs, DeepONets, or Fourier Neural Operators (FNOs). Direct experience using frameworks like NVIDIA Modulus, DeepXDE, or PyTorch Geometric.
Mathematical Depth: Exceptional understanding of partial differential equations (PDEs), vector calculus, automatic differentiation (autograd), and numerical optimization algorithms (Adam, L-BFGS).
Data Pipelines: Strong proficiency in manipulating spatial or geometric datasets using Python libraries (NumPy, SciPy, Shapely, Open3D, or custom voxelization matrices).
