Netholabs is a neuroscience and AI research company building biological foundation models grounded in large-scale neurobehavioral data. It designs custom hardware, high-density neural recording systems and tracking environments to capture petascale datasets, working towards whole brain emulation. The company has offices in London and San Francisco and a research site at the University of Sussex in Brighton.

About the role

This is an entry-level role supporting the research and engineering team across model training, data pipelines and applied ML work. It offers hands-on exposure to how a neural foundation model gets built, from raw neurobehavioral data through training runs to downstream applications in robotics and embodied AI.

Model development

• Support training, fine-tuning and evaluation of neural foundation models.
• Run experiments, track results and help iterate on model architectures.
• Work with biomechanical data, machine vision data and robotics control problems.
• Benchmark model performance and write up findings.

Data and infrastructure

• Build and maintain data pipelines for petascale neurobehavioral datasets.
• Clean, preprocess and structure multi-modal data across video, sensor and physiological streams.
• Keep experiment tracking, datasets and compute usage organized.

Applied ML and robotics

• Support applications of trained models to robotics and embodied-agent tasks.
• Prototype tools, scripts and demos to test model capabilities.

What they are looking for

• Strong Python and comfort in a Linux command-line environment.
• A solid foundation in ML fundamentals and experience with at least one deep learning framework, PyTorch preferred.
• Experience training ML models on time-series datasets.
• Valued: machine vision or robotics problems, large-scale or distributed training, data pipelines, or a background in neuroscience or behavioral science.

No prior neuroscience or robotics experience is required. Candidates must be eligible to work in the US or the UK; visa sponsorship is not available.