University of Minnesota
Research Engineer - Research Computing (Research Professional 2)
University of Minnesota, Minneapolis, Minnesota, United States, 55400
About the Job
The Translational Neural Engineering Laboratory in the University of Minnesota Department of Psychiatry is seeking a Research Engineer interested in working at the intersection of technology, neuroscience, and mental health. Our laboratory develops technologies for changing activity in distributed brain networks involved in severe mental illnesses such as PTSD, major depression, addiction, and obsessive-compulsive disorder. Some of them are in pilot clinical trials or being prepared to enter those trials. To understand our target circuits and prove that we can change them, we record electrical brain signals and deliver targeted stimulation in both model animal systems and human volunteers, across a range of techniques (both invasive and non-invasive). Much of our work borrows ideas from brain-computer interface/neural prosthetic technologies.
This posting is for a support/cross project role. You will work in collaboration with the lab's experimentalists to develop, maintain, and extend pipelines for data analysis. The goal of these pipelines is to fuse signals from video, physical sensing (e.g., beam breaks and switches), and direct electrical brain recordings to understand the biological basis of mental illness. Concepts from modern machine learning and predictive modeling are woven throughout, in both supervised and unsupervised paradigms. Almost all of our analyses involve frequency-domain (Fourier/wavelet and related transform) analysis. The current codebase is a mixture of Python, R, and MATLAB, with an increasing emphasis on the first two and on the use of open-source/reusable toolkits. We work with data in a wide range of formats, and the design of scripts/tools to flexibly ingest and merge data across those formats is another central part of the work.
#J-18808-Ljbffr
This posting is for a support/cross project role. You will work in collaboration with the lab's experimentalists to develop, maintain, and extend pipelines for data analysis. The goal of these pipelines is to fuse signals from video, physical sensing (e.g., beam breaks and switches), and direct electrical brain recordings to understand the biological basis of mental illness. Concepts from modern machine learning and predictive modeling are woven throughout, in both supervised and unsupervised paradigms. Almost all of our analyses involve frequency-domain (Fourier/wavelet and related transform) analysis. The current codebase is a mixture of Python, R, and MATLAB, with an increasing emphasis on the first two and on the use of open-source/reusable toolkits. We work with data in a wide range of formats, and the design of scripts/tools to flexibly ingest and merge data across those formats is another central part of the work.
#J-18808-Ljbffr