Physics ML Engineer: Real-Time, Multi-Modal Pipelines

Visible Hands; New York (NY); On-site; USD 150,000 - 190,000; Full time

Job summary

Root Access, a NYC-based frontier electronics startup, seeks a PhD-level machine learning researcher to design and train physics-informed models and advanced data pipelines.

You will collaborate with engineers across electrical, firmware, software, and ML to map schematics to spatial engines, optimize for real-time execution on GPU clusters, and advance SciML methods.

This role demands strong PDE knowledge, experience with PyTorch/JAX, and hands-on data handling of geometric datasets.

Qualifications

• Master’s or Ph.D. in CS, Math, EE, or Physics with SciML focus is required.
• 4+ years with PyTorch or JAX in research or deployment.
• Hands-on experience building/training PINNs, FNOs, etc.
• Strong PDEs, vector calculus, autograd, and numerical optimization knowledge.
• Experience handling spatial/geometric data with Python.

Responsibilities

• Architect Physics Foundation Models for real-world physics tasks.
• Build ECAD data pipelines to convert PCB files to continuous space data.
• Integrate multi-modal architectures mapping schematics to spatial engines.
• Optimize training and inference on GPU clusters for real-time use.

Skills

PyTorch

JAX

SciML

PINNs

FNOs

Python (NumPy SciPy)

Open3D

Shapely

Voxelization

Education

Master’s or PhD in quantitative field with SciML focus

Tools

NumPy

SciPy

Shapely

Open3D

Job description

Root Access, a NYC-based frontier electronics startup, seeks a PhD-level machine learning researcher to design and train physics-informed models and advanced data pipelines.

You will collaborate with engineers across electrical, firmware, software, and ML to map schematics to spatial engines, optimize for real-time execution on GPU clusters, and advance SciML methods.

This role demands strong PDE knowledge, experience with PyTorch/JAX, and hands-on data handling of geometric datasets.