About this opportunity
5V Tech lists this Machine Learning Engineer opportunity in new york, New York. Review the employer’s description below for duties, qualifications and application requirements.
Job description
Total Comp: Base + Equity + Bonus, Standard Benefits
About the company
This is a frontier deep tech company: a NYC-based startup backed by top-tier investors, building at the intersection of machine learning, physics, and advanced electronics. The team blends engineers across electrical, firmware, software, and machine learning, all working on technology designed to bridge the gap between AI and the physical world.
About the role
We're recruiting a Machine Learning Engineer to work on the development of physics foundation models and the infrastructure behind them. You'll be tackling highly technical problems across deep learning, scientific computing, geometry, and physics, building models that can learn from complex physical systems and engineering data.
You'll work closely with a small team of exceptional engineers, taking ideas from research through to working systems. This is a build fast, solve hard problems kind of role, ideal for an ML engineer who wants to work on problems that sit well beyond conventional AI applications.
Key responsibilities
Design and train deep learning models for physics foundation model applications
Develop high performance data pipelines that convert geometric, discrete, and multi-layer engineering data into continuous spatial representations
Work with complex engineering file formats including ODB++, IPC-2581, STEP, Gerber, and related datasets
Collaborate on connecting upstream Graph Neural Networks or LLMs that map schematic topologies to downstream spatial physics engines
Develop representations and processing pipelines for complex spatial and geometric datasets
Build and optimise training and inference pipelines running on GPU clusters
Experiment with Scientific Machine Learning approaches including Physics Informed Neural Networks (PINNs), Fourier Neural Operators (FNOs), and related architectures
Work closely with software, electrical, firmware, and machine learning engineers throughout the development process
Optimise models and inference systems for real-time execution and computational efficiency
Ideal profile
Master's or Ph.D. in Computer Science, Mathematics, Electrical Engineering, Physics, or a related quantitative field with a focus on Scientific Machine Learning
4+ years of expert-level experience with PyTorch or JAX
Direct, hands‑on experience building and training PINNs, FNOs, or similar Scientific ML architectures
Exceptional understanding of partial differential equations, vector calculus, automatic differentiation, and numerical optimisation
Strong understanding of optimisation algorithms such as Adam and L-BFGS
Strong Python skills and experience working with scientific computing libraries such as NumPy and SciPy
Experience manipulating spatial, geometric, or other complex structured datasets
Preferred qualifications
Experience with Graph Neural Networks, LLMs, neural operators, or other multi-modal architectures
Experience working with engineering, CAD, PCB, simulation, or other physical system datasets
Proficiency with Shapely, Open3D, voxelisation techniques, or custom spatial matrices
Experience working with GPU clusters and large-scale model training
Experience optimising machine learning models for real-time or low-latency inference
Background in computational physics, numerical methods, computational geometry, or simulation
Experience connecting multiple ML architectures into a larger end-to-end system
Experience taking research concepts through to production
#J-18808-Ljbffr
Worksite address
new york, NY, 10261, US
Who can apply
Review the original listing for work authorization, qualifications and employer requirements.