Machine Learning Engineer

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

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).