Machine Learning Engineer

Root Access • New York, NY

32d • Onsite

About The Position

Root Access is a frontier electronics company. We are a NYC-based startup funded by top investors. Our team is a passionate mix of engineers across electrical, firmware, software, and machine learning.

Requirements

• Master’s or Ph.D. in Computer Science, Mathematics, EE, Physics, or a related quantitative field with a focus on Scientific Machine Learning (SciML).
• 4+ years of expert-level experience with PyTorch or JAX.
• 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.
• Exceptional understanding of partial differential equations (PDEs), vector calculus, automatic differentiation (autograd), and numerical optimization algorithms (Adam, L-BFGS).
• Strong proficiency in manipulating spatial or geometric datasets using Python libraries (NumPy, SciPy, Shapely, Open3D, or custom voxelization matrices).

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.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior