Vaibhavi Itkyal
Applied Scientist at Amazon
Seattle, Washington, United States
Summary
🎓
Top SchoolVaibhavi Itkyal is an applied scientist and machine learning engineer with eight years of interdisciplinary experience building production-ready AI systems across finance, infrastructure optimization, and healthcare. She designs and deploys end-to-end solutions for forecasting, personalization, and decision intelligence using transformers, LLMs, multimodal fusion, and interpretable models, with a track record of shipping scalable systems at Amazon and in global research labs. Her PhD work fused structural and functional neuroimaging to build multimodal PyTorch models that achieved >94% benchmark accuracy and applied SHAP for subgroup analysis, reflecting a strong focus on interpretable, population-scale AI. Vaibhavi pairs hands-on platform engineering—such as time-series and Kubernetes scaling projects—with academic rigor from IIT Madras, UPenn, and UQ, and contributes practical computer vision code to open-source TensorFlow repositories. She excels at bridging experimental research with business-aligned deployment, often leading cross-functional teams to turn complex signals into actionable products.
7 years of coding experience
5 years of employment as a software developer
Indian Institute of Technology MadrasFergusson CollegeDr Kalmadi Shamarao High SchoolDoctor of Philosophy - PhD, Computational Neuroscience, Doctor of Philosophy - PhD, Computational Neuroscience at Emory University
Github Skills (5)
computer-vision10
jupyter-notebook10
tensorflow10
python10
image-processing10
Programming languages (3)
Github contributions (5)
shakes76/PatternFlow
Oct 2019 - Oct 2019
Pattern recognition and image processing library for Tensorflow
Role in this project:
ML Engineer
ML EngineerContributions:32 commits, 1 PR in 1 day
Contributions summary:Vaibhavi contributed to the implementation of image processing techniques using the Sobel transform within a Jupyter Notebook environment. They developed and refined Python code, utilizing the TensorFlow library for edge detection. The commits demonstrate the creation of notebooks for horizontal, vertical edge detection, and edge magnitude calculation, indicating a focus on computer vision within the TensorFlow framework.
recognitionimage-processing-libraryprocessing-libraryimage-processingpattern-recognition
vaibhavi5/PialNet
Jan 2021 - Feb 2023
Repo for the 2020 UQ Summer School of AI Hackathon project: "Segmentation of Magnetic Resonance Angiography data"
Contributions:1 PR, 1 push in 2 years 1 month
pytorchsummer-schoolmagneticresonancedeep-learning
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.