ML/AI Engineer

Bridge Neurotech, Inc. is hiring an ML/AI Engineer (onsite) to build and scale the models and infrastructure behind its neural decoding pipeline. Responsibilities

Design, implement, train, and evaluate models across the pipeline, including

fUSI reconstruction ,

signal preprocessing , and

downstream decoding ; own results for the components you lead Drive an

experimental agenda

for your area: form and test hypotheses when a model is not learning, run ablations, and tune architectures, losses, and training schedules Extend models to new data regimes such as new dimensionalities (for example

2D to 3D volumetric ), new probes, and new subjects; build preprocessing pipelines to normalize data for training Own training infrastructure:

experiment tracking ,

config management ,

checkpointing ,

mixed-precision ,

multi-GPU training , and

profiling , built so others can rely on it Define evaluation strategy with

metrics , pre-launch tests, and

regression checks

to confirm real model improvements Debug numerical and performance issues including

NaNs under mixed precision , silent shape bugs, page-cache thrashing, dead gradients, and GPU memory ceilings Build inference paths for

full-volume reconstruction

and

low-latency real-time decoding Collaborate with imaging scientists and neuroscientists to understand data sources and artifacts, and help shape how future data is collected Track relevant literature in

neural operators ,

neuroimaging , and

neural decoding ; reproduce key results for the roadmap and propose next steps Review code and designs; help onboard new engineers and interns as the team grows Requirements

PhD

in machine learning, computer science, electrical engineering, computational neuroscience, physics, or a related field; or a

bachelor’s or master’s degree

in one of those fields plus

2 to 3 years

of experience building and shipping machine learning systems in a research or product setting Strong

Python

and hands‑on

PyTorch

development (or an equivalent framework such as

JAX

or

TensorFlow ) Track record of independently taking a model from

paper/prototype

to something that trains reliably on

real data Evidence of end‑to‑end ownership of an open‑ended technical problem (thesis, publications, open‑source work, or shipped system) Comfort with large numerical datasets (hundreds of gigabytes to multiple terabytes) and

memory‑mapped arrays Solid grounding in first principles such as

linear algebra

and

signal processing GPU proficiency:

mixed precision ,

memory profiling ,

gradient checkpointing , and diagnosing bottlenecks Strong software engineering practices including

version control ,

testing ,

code review , and coding conventions Self‑directed and self‑motivated; able to execute on a goal without step‑by‑step guidance Technologies

Python PyTorch JAX TensorFlow Benefits

Excellent medical benefits 6% match 401(k) Nice to Have

Experience with neural operators (FNO), implicit neural representations, or physics‑informed machine learning architectures Exposure to neural decoding, brain‑computer interfaces, or neuroimaging data Familiarity with complex‑valued neural networks or spectral methods Experience developing real‑time or low‑latency inference systems Distributed or multi‑GPU training at scale Publications at machine learning or neuroscience venues, or contributions to open‑source machine learning tooling Prior work in a startup or small team, or evidence of thriving without much scaffolding Role focus:

Own and scale key parts of the models and infrastructure behind a neural decoding pipeline from functional ultrasound acquisition through image reconstruction, preprocessing, and decoding; work at the frontier of neural decoding and foundation models.

#J-18808-Ljbffr