Senior researcher
ITL’s role in the IMS project “Distributed Manufacturing of First-In-Class NIST Traceable Active
Cell Reference Materials” involves the following tasks: (1) the design and training of convolutional
neural networks (CNN) for cell segmentation, cell division detection across time, and label-free cell
viability assessment under different imaging modalities, and (2) the design of reference materials with
which to transfer AI models across labs. Our success depends upon the availability of highly skilled
domain experts. We are challenged with difficult tasks that require not only expertise in running
different types of CNNs, but also in designing new architectures for applications where training data is
scarce but high accuracy is paramount.
Reference Material Creation to Calibrate AI Solutions Across Labs
- A PhD degree in Computer Science with 3 or more years of relevant experience.
- Expertise in PyTorch/Python and state of the Art AI models like vision transformers and advanced
CNNs. - Ability to build deployable complex software solutions for cell image analysis.
- Strong oral and written communication skills and strong presentation skills.
Key responsibilities will include but are not limited to:
- Developing new AI architectures for meniscus removal using image-to-image regression networks.
- Create a solution that can generalize the meniscus removal regardless of the content being imaged.
- Create a model that predicts an image quality metric based on a group of existing blur metrics from
the literature and compare that solution with a regular convolutional neural network. - Produce high-quality publications based on research and results present at internal and external
meetings and conferences.