Machine Learning Engineer

Root Access, Inc.; New York (NY); On-site; USD 140,000 - 190,000; Full time

Job summary

Root Access, Inc. is a NYC-based frontier electronics startup building cutting-edge physics-informed AI. The team blends electrical, firmware, software, and ML expertise to push performance in real-time systems.

The role focuses on architecting physics foundation models, developing a robust ECAD data pipeline, and enabling seamless integration of graph neural networks with spatial physics engines, all while optimizing for GPU-based training and inference.

Qualifications

• Master’s or Ph.D. in a quantitative field with SciML focus.
• Deep learning framework experience with PyTorch or JAX.
• Hands-on SciML experience building/training PINNs, FNOs, etc.
• Strong mathematical depth in PDEs, vector calculus, autograd, and optimization.
• Experience manipulating spatial/geometric datasets with Python libraries.

Responsibilities

• Architect Physics Foundation Models: design and train deep learning models.
• Build the ECAD Data Pipeline: convert PCB data to continuous space.
• Multi-Modal Architecture Integration: connect GNNs/LLMs to spatial engines.
• Optimize for Real-Time Execution: optimize training/inference on GPU clusters.

Skills

PyTorch

JAX

SciML

PDEs

Automatic Differentiation

Numerical Optimization

Python

Data Pipelines

Education

Master’s or Ph.D. in Computer Science, Mathematics, EE, Physics

Tools

Open3D

Shapely

NumPy

SciPy

Job description

About the company

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.

Core Responsibilities

• Architect Physics Foundation Models: Design and train deep learning models.

• 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 space data.

• 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.

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, FNOs, etc.

• 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).