What are the responsibilities and job description for the ASPIRE Intern – Brain Science: Applying Machine Learning for Dynamic Autofocus in Transmission Electron Microscopy position at Allen Institute?
ASPIRE Intern – Brain Science: Applying Machine Learning for Dynamic Autofocus in Transmission Electron Microscopy
The mission of the AllenInstitute is to understand the principles that govern life and to advance health. Our creative and multi-dimensional teams focus on answering some of the biggest questions in bioscience. We accelerate foundational research, catalyze bold ideas, develop tools and models, and openly share our science to make a broad, transformational impact on the world.
The mission of the Allen Institute for Brain Science is to accelerate the understanding of how the human brain works in health and disease. Using a big science approach, we generate useful public resources, drive technological and analytical advances, and discover fundamental brain properties through integration of experiments, modeling and theory.
The field of neuroscience has never been closer to uncovering the wiring diagram of the mammalian brain. The brain’s wiring diagram, or connectome, is one of the main components underlying brain function. The use of volumetric transmission electron microscopy (TEM) as a technology to successfully produce large-scale wiring diagrams at synaptic resolution has been recently demonstrated on the scale of the cubic millimeter. Uncovering the brain’s connectome requires pushing the technology past the cubic millimeter to the whole mouse brain. However, scaling up tissue samples from the millimeter to the centimeter range introduces new obstacles in acquiring high-quality images. To address this, we are leveraging automation techniques to collect high-quality TEM data of whole mouse hemisphere sections.
We are seeking an intern to contribute to the efforts of the Connectomics department at the Allen Institute in developing automation tools for high-throughput TEM imaging of whole hemisphere samples. Building from our previous automated imaging pipeline used to image the cubic millimeter of mouse visual cortex, we leverage traditional computer vision techniques to automate the tuning of microscope parameters to acquire high-quality TEM images in a modular software framework. Our current approach uses classical algorithms to tune microscope parameters for focus and image quality at the outset of imaging an individual section. Machine learning approaches offer an alternative strategy to perform dynamic parameter adjustment to continuously acquire high-quality images. Such machine learning approaches for focus and image quality have recently been described for scanning electron microscopes (SEM), resulting in the dynamic tuning of microscope parameters to improve image quality during acquisition.
The intern’s project will first seek to apply this published method of machine learning in SEM to TEM image acquisition. Specifically, the intern will explore this alternative parameter tuning approach by expanding on existing deep learning focus correction models and leveraging our established automation efforts to perform dynamic image focus corrections during TEM image acquisition. Using an open-source machine learning library for computer vision, the intern will develop deep learning image correction methods using images the intern acquires on our TEMs. After completion of this machine learning modeling project, we will evaluate its utility by integrating it into our modular software framework and comparing its output with our classical computer vision approach. Through this project, the intern will gain experience evaluating microscopy data for image quality, training machine learning models with TEM image data, and learn to apply cutting-edge methods in computer vision to an image acquisition pipeline. Overall, the project will allow the intern to work with large data acquisition pipelines at the forefront of TEM imaging, develop software skills while working collaboratively on production codebases, and contribute to cutting-edge neuroscience research.
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.
Applications must be received by January 12, 2026, to be considered.
Educational Objectives
The mission of the AllenInstitute is to understand the principles that govern life and to advance health. Our creative and multi-dimensional teams focus on answering some of the biggest questions in bioscience. We accelerate foundational research, catalyze bold ideas, develop tools and models, and openly share our science to make a broad, transformational impact on the world.
The mission of the Allen Institute for Brain Science is to accelerate the understanding of how the human brain works in health and disease. Using a big science approach, we generate useful public resources, drive technological and analytical advances, and discover fundamental brain properties through integration of experiments, modeling and theory.
The field of neuroscience has never been closer to uncovering the wiring diagram of the mammalian brain. The brain’s wiring diagram, or connectome, is one of the main components underlying brain function. The use of volumetric transmission electron microscopy (TEM) as a technology to successfully produce large-scale wiring diagrams at synaptic resolution has been recently demonstrated on the scale of the cubic millimeter. Uncovering the brain’s connectome requires pushing the technology past the cubic millimeter to the whole mouse brain. However, scaling up tissue samples from the millimeter to the centimeter range introduces new obstacles in acquiring high-quality images. To address this, we are leveraging automation techniques to collect high-quality TEM data of whole mouse hemisphere sections.
We are seeking an intern to contribute to the efforts of the Connectomics department at the Allen Institute in developing automation tools for high-throughput TEM imaging of whole hemisphere samples. Building from our previous automated imaging pipeline used to image the cubic millimeter of mouse visual cortex, we leverage traditional computer vision techniques to automate the tuning of microscope parameters to acquire high-quality TEM images in a modular software framework. Our current approach uses classical algorithms to tune microscope parameters for focus and image quality at the outset of imaging an individual section. Machine learning approaches offer an alternative strategy to perform dynamic parameter adjustment to continuously acquire high-quality images. Such machine learning approaches for focus and image quality have recently been described for scanning electron microscopes (SEM), resulting in the dynamic tuning of microscope parameters to improve image quality during acquisition.
The intern’s project will first seek to apply this published method of machine learning in SEM to TEM image acquisition. Specifically, the intern will explore this alternative parameter tuning approach by expanding on existing deep learning focus correction models and leveraging our established automation efforts to perform dynamic image focus corrections during TEM image acquisition. Using an open-source machine learning library for computer vision, the intern will develop deep learning image correction methods using images the intern acquires on our TEMs. After completion of this machine learning modeling project, we will evaluate its utility by integrating it into our modular software framework and comparing its output with our classical computer vision approach. Through this project, the intern will gain experience evaluating microscopy data for image quality, training machine learning models with TEM image data, and learn to apply cutting-edge methods in computer vision to an image acquisition pipeline. Overall, the project will allow the intern to work with large data acquisition pipelines at the forefront of TEM imaging, develop software skills while working collaboratively on production codebases, and contribute to cutting-edge neuroscience research.
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.
Applications must be received by January 12, 2026, to be considered.
Educational Objectives
- Develop understanding of basic transmission electron microscopy theory and operation
- Gain understanding of leveraging automation techniques for electron microscopy
- Learn about neuroanatomy and ultrastructure of the mouse brain
- Learn to write clean, reproducible, documented code in a collaborative setting using GitHub version control and code reviews
- Communicate progress and findings to relevant teams within the Allen Institute
- Bachelor’s degree
- Demonstrated commitment to science
- Prior coding experience in Python is preferred
- Prior experience with PyTorch and/or training neural networks is helpful
- Laboratory environment - possible exposure to chemical, biological, or other hazardous substances.
- This may include wearing personnel protective equipment (PPE)
- Fine motor movements in fingers/hands to operate computers and other office equipment
- Repetitive motion with lab equipment
- This role is currently working onsite and is expected to work onsite for the majority of working hours. The primary work location for this role is 615 Westlake Ave N., with flexibility to work remotely on a limited basis.
- Must have completed a Bachelor’s degree prior to the start of the program, and no earlier than December 1, 2023, and must not have an advanced degree in field relevant to the role/project
- Must be able to start in June or July 2026 and commit to the full one-year program, which will end on May 28, 2027
- Must be authorized to work in the U.S. for the program duration
- Must be 18 years of age or older
- ASPIRE Interns are expected to participate as fully-engaged team members, attending and participating in team meetings, presenting on their work, etc.
- Aside from program activities, interns are expected to work full-time as regular team members unless otherwise approved by their manager
- **Please note, this opportunity offersrelocation assistance**
- **Please note, this opportunity requires U.S work authorization and does not sponsor work visas**
- $61,048 (non-negotiable)
- ASPIRE Interns (and their families) are eligible to enroll in benefits per eligibility rules outlined in the Allen Institute’s Benefits Guide. These benefits include medical, dental, vision, and basic life insurance. Employees are also eligible to enroll in the Allen Institute’s 401k plan. Paid time off is also available as outlined in the Allen Institutes Benefits Guide. Details on the Allen Institute’s benefits offering are located at the following link to the Benefits Guide: https://alleninstitute.org/careers/benefits .
Salary : $61,048
ASPIRE Intern – Brain Science: Software Engineering - High-Throughput Data Ingest in the Brain Knowledge Platform
Allen Institute -
Seattle, WA
Product Manager - Electron Microscopy
Bruker Daltonics -
Bellevue, WA
Product Manager - Electron Microscopy
Bruker -
Seattle, WA