Intern - Machine Learning Neuroscience

Intern - Machine Learning for Neuroscience

Research Intern – Machine Learning for Neuroscience

The Allen Institute accelerates science for a healthier world through large-scale research designed to answer some of the most complex questions in biology. Our multi-disciplinary teams generate foundational knowledge, tools, and data to understand how our brain, cells, and immune system work. We share our work openly so others can build on it, move faster, and ask bigger questions. We drive discovery forward and create new possibilities for improving human health.

The goal of the Neural Dynamics accelerator is to understand how the brain generates flexible behavior. We aim to uncover the algorithms—implemented by dynamics in brain-wide neural circuits—that allow animals to build internal models, process information, and choose actions.

We are searching for a graduate student intern who will analyze large-scale neural and behavioral recordings to uncover how populations of neurons coordinate to control movement.

This is a one-year, part-time research position at the intersection of machine learning and neuroscience. The intern will work with a rich existing dataset: two intermingled but genetically distinct populations of neurons in the striatum, recorded simultaneously, with individual cells tracked stably across many days, alongside a continuously measured motor output and synchronized muscle activity and video. The central question is a latent-variable modeling problem — how do the two populations jointly encode the motor output, and how much of their activity is shared between them versus private to each?

Understanding how these circuits specify movement is also foundational for closed-loop brain-machine interfaces that aim to restore movement after injury or disease, an active area of work in the team. No prior neuroscience background is required; the intern will be mentored directly. The position is a one-year commitment so that the intern has time to carry a project through to a scientific result, and strong work may contribute to a conference presentation or publication.

Students at the University of Washington may be able to arrange academic credit for this work, including toward a master’s thesis, in coordination with their degree program and faculty advisor.

At the Allen Institute, we believe that science is for everyone – and should be open to everyone. We are dedicated to combating biases and reducing barriers to STEM careers more broadly.

We also believe that science is better when it includes different perspectives and voices. We strive to make the Allen Institute a place where everyone feels like they belong and are empowered to do their best work in a supportive environment.

We are an equal-opportunity employer and strongly encourage people from all backgrounds to apply for our open positions.

** A cover letter is required to be considered for this position.**

• Characterize how coordinated activity across two simultaneously recorded neural populations encodes forelimb force
• Implement, fit, and evaluate machine learning and latent variable models that partition shared versus population-specific covariance, and benchmark them against recently published alternatives
• Relate neural population activity to behavioral variables using regression and classification methods, with appropriate cross-validation and controls
• Extend the analysis to electromyography (EMG) and synchronized behavioral video, and to how neural coding and behavior change across days of learning
• Produce documented, version-controlled Python analysis code that other team members can build on
• Communicate results to the mentoring scientists and the wider team, and contribute figures and methods text toward…