Research Scientist, Deep Learning Models

Jobverse.io; Cambridge (OH); On-site; USD 90,000 - 150,000; Full time

Job summary

Mindspan Institute in the nonprofit research sector seeks a Research Scientist to design, train, and evaluate deep learning models for microscopy data and to collaborate with other teams to integrate models into imaging pipelines.

You will conduct controlled experiments, perform ablations and error analysis, and ensure all work is documented with reproducible methods and clear reasoning to guide future model development.

Responsibilities

• Design, train, and evaluate deep learning models for volumetric microscopy data, including segmentation and object detection
• Build methods to stitch and align image tiles and serial sections into consistent volumes
• Adapt pretrained vision models to our imaging modalities and judge when new architectures are warranted
• Run controlled experiments with ablations, held-out evaluation, and error analysis
• Collaborate with pipeline and annotation teams to productionize models and obtain required ground truth
• Document experiments and provide reproducible records and justification for design choices

Job description

Mindspan Institute is a nonprofit research institute developing tools to analyze the human brain. The Research Scientist will design, train, and evaluate deep learning models for microscopy data, and collaborate with other teams to integrate models into imaging pipelines and share reproducible methods.

Responsibilities

• Design, train, and evaluate deep learning models for volumetric microscopy data, including dense segmentation, boundary and affinity prediction, and object detection
• Build models and methods that stitch and align image tiles and serial sections into consistent volumes
• Adapt pretrained and foundation vision models to our imaging modalities, and decide when a new architecture is worth the cost
• Run controlled experiments: ablations, held-out evaluation, and error analysis that shows which failure modes a change fixed and which it introduced
• Work with the pipeline and annotation teams to move models into production, and to request the ground truth that the next model needs
• Documentation and training: keep experiment records that others can reproduce, with the reasoning behind each design choice