Jeya Jose
Senior Researcher at Microsoft
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolJeya Jose is a senior researcher at Microsoft Research with 9 years of experience building multimodal AI and foundation models for medical applications, spanning radiology, pathology and population-scale virtual patient frameworks. Prior to Microsoft she was a postdoc at Stanford (AIMI) and earned her PhD and MS from Johns Hopkins, where she developed state-of-the-art methods in segmentation, image enhancement, and vision-language models. Her work on gated axial-attention for medical image segmentation (Medical Transformer) and other projects has produced 40+ publications, three US patents, and multiple best-paper and fellowship awards. Jeya blends deep technical expertise in diffusion models, generative AI and model adaptability with practical engineering—her GitHub contributions show hands-on implementation of axial attention and position-embedding refinements used in medical CV codebases. She is focused on translating large-model capabilities into clinically valuable representations and novel spatial-medicine insights that connect tissue architecture, cell states, and molecular signals.
8 years of coding experience
7 years of employment as a software developer
Johns Hopkins UniversityHigher Secondary, CBSE, Computer Science Stream, 95.2%, Higher Secondary, CBSE, Computer Science Stream, 95.2% at Maharishi International Residential School , ChennaiBachelor of Technology (B.Tech.), Instrumentation and Control Engineering, Bachelor of Technology (B.Tech.), Instrumentation and Control Engineering at National Institute of Technology TiruchirappalliICSE, ICSE at Vikaasa School , MaduraiPosdoctoral, Computer Science, Radiology, Posdoctoral, Computer Science, Radiology at Stanford University
English, Tamil
Github Skills (13)
attention-mechanism10
transformers10
pytorch10
deep-learning10
python10
medical-image-analysis10
segmentation9
image-segmentation9
medical-imaging9
algorithms8
data-structures8
algorithm8
data-structure8
Programming languages (3)
Github contributions (5)
jeya-maria-jose/Medical-Transformer
Feb 2021 - Mar 2022
Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation" - MICCAI 2021
Role in this project:
ML Engineer
ML EngineerContributions:32 commits, 1 PR, 23 pushes in 1 year 1 month
Contributions summary:Jeya primarily contributes to the core functionality of the medical transformer model. Their commits involve significant modifications to the `axialnet.py` file, indicating their focus on the implementation and refinement of the axial attention mechanism. The updates include changes related to position embeddings and dynamic attention mechanisms. Additionally, they updated testing procedures and added citations suggesting model development and evaluation efforts.
pytorchmiccaitransformersmedical-imagedeep-learning
jeya-maria-jose/KiU-Net-pytorch
Jun 2020 - May 2022
Official Pytorch Code of KiU-Net for Image/3D Segmentation - MICCAI 2020 (Oral), IEEE TMI
Contributions:1 release, 47 commits, 39 pushes in 1 year 11 months
semantic-segmentationunet-image-segmentationmedical-image-segmentationtmikiunet
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.