Machine Learning Engineer

Netholabs•San Francisco, CA

2d•Onsite

About The Position

We’re building a foundation model of the brain and behavior across species, trained on large-scale multimodal neural and behavioral data, including EEG, MEG, and fMRI. This role is central to designing and training the model. You’ll work on the core generative model, including its architecture, training at scale, and representation learning across neural signals and behavior, as well as research questions involved in modeling biological data as sequences. You’ll join a small team and work alongside the existing ML engineer, with room to shape the modeling direction as the company grows. This early-stage role involves training greenfield models, owning parts of the stack, and contributing to the company’s core asset. The position is full-time and in person in San Francisco. Applicants must already be based in the United States and able to work in person in San Francisco. Relocation is not supported.

Requirements

Experience training large deep learning models end to end in production or research settings.
Hands-on experience training transformers or other large sequence models, including distributed training and scaling.
Proficiency in Python and PyTorch, with clean, concise coding practices and discipline in writing reproducible model code.
Strong implementation and prototyping skills, and comfort working across research and engineering at scale.
Comfort working with large, messy, multimodal, or time-series data.
Ability to learn new domains quickly, orient oneself in academic literature, and implement new ideas.
An organized, methodical approach to research, with excellent communication and collaboration skills.
Pragmatism suited to an early-stage environment where the role owns work end to end.

Nice To Haves

Enthusiasm for modeling biological data, the intersection of the brain and AI, and building foundation models for neural data such as EEG, MEG, and fMRI.
Experience with representation learning and self-supervised or generative modeling, such as VAEs, GANs, diffusion models, and contrastive learning.
Background or strong interest in neuroscience, biosignals, or computational cognitive science.
Familiarity with signal processing, especially for EEG, and time-series analysis.
Experience training on large-scale, multi-node GPU clusters, or with hyperparameter optimization, training infrastructure, or evaluation frameworks.
Experience contributing to large existing codebases and ramping up quickly.
Published machine learning research in well-respected venues, or open-source contributions in relevant areas.

Responsibilities

Design, train, and iterate on large generative recurrent or transformer-based models over multimodal neural and behavioral data.
Own training at scale, including data loading, distributed multi-node training, hyperparameter optimization, and evaluation.
Develop representations that capture structure across species and modalities.
Train models on animal and human behavioral data, as well as direct neural data.
Take ownership of distinct modeling-stack components and deliver them as working, well-documented modules.
Define and run experiments to test modeling choices, and build evaluations to determine whether the model is learning what is needed.
Use neuroscience and sequence-modeling literature to inform architecture and training, adapting ideas from modalities such as vision, audio, and language to EEG and other neural signals.
Rapidly prototype ideas and turn research findings into reproducible, production-quality model code.
Partner with the data engineering team on data readiness and with the research team on what the model needs to capture.
Contribute to the shared modeling roadmap alongside the existing ML engineer.
Communicate processes, results, and trade-offs clearly to technical and scientific colleagues.