# Sumeha Kashyap

> Notification Recommendation @ YouTube

Location: San Francisco, California, United States
Profile: https://flows.cv/sumeha

I am a CS grad student at UMass, Amherst seeking full time opportunities in Machine Learning and Software Development roles. I have worked for 2 years at Samsung Research’s Visual Understanding Division on developing real time, on-device deep learning solutions for various unconstrained image understanding problems like image classification, object detection and human object interaction understanding. I have experience working in PyTorch and building time and space efficient neural network architectures. 
At UMass I am currently taking coursework in Neural Networks, Natural Language Processing and Machine Learning.

## Work Experience
### Senior Software Engineer @ YouTube
Jan 2021 – Present

### Machine Learning Intern @ PathAI
Jan 2020 – Jan 2020 | Boston, Massachusetts, United States
Used Multiple Instance Learning to improve disease classification in images spanning millions of pixels.
Implemented an unsupervised learning technique called Contrastive Predictive Coding to create image representations that leverage unlabeled data

### Graduate Student Researcher @ Amazon
Jan 2020 – Jan 2020
Alexa-NLU. Common Sense Reasoning.

### Machine Learning Engineer @ Samsung India
Jan 2017 – Jan 2019 | Bangalore, India
Was a member of the Visual Understanding Division where I made the following contributions:
1)Trained deep neural networks for image classification and object detection in Caffe and Tensorflow.
2)Brainstormed and implemented different training techniques for fast and robust on device real time image classification.  Developed new methods to reduce training time for a continuously expanding category catalogue.  
3) Designed a novel architecture for Human Object Interaction Detection which achieved close to state of the art accuracy on public data sets. 
4)Further refined the architecture to reduce model complexity and size. Experiments done  in Pytorch and Tensorflow. 
Above solutions are commercialized in Bixby Vision employed in S9 Samsung Series, Photo Gallery of S10 and upcoming S11 Samsung Series. 
5) Worked with other  team members on Salient Moment Detection in Videos, Video Classification, Instance and Semantic Segmentation.

### Summer Research Intern @ McGill University
Jan 2016 – Jan 2016 | Montreal, Canada Area
Added street crossing alignment functionality to Autour, an eyes-free mobile system
for the blind using image processing algorithms to identify crossings and orient the
user accordingly. Advised by Dr Jeremy Cooperstock.

### Summer Research Intern @ Indian Institute of Technology, Hyderabad
Jan 2015 – Jan 2015
Obtained a 3D model of choroid vessels from several 2D image slices using a level
set method based approach focused on minimizing a mutual information based  surface energy to obtain the optimal fit.  Advised by Dr Soumya Jana

### Robotics Module Organiser @ Techniche, IIT Guwahati
Jan 2013 – Jan 2014 | IIT Guwahati

### Technothlon Organiser @ Techniche, IIT Guwahati
Jan 2013 – Jan 2014


## Education
### Master's degree in Computer Science
University of Massachusetts Amherst

### Bachelor's degree | Major in ECE with a Minor in Computer Science and Engineering in Computer Science
Indian Institute of Technology, Guwahati


## Contact & Social
- LinkedIn: https://linkedin.com/in/sumeha-kashyap

---
Source: https://flows.cv/sumeha
JSON Resume: https://flows.cv/sumeha/resume.json
Last updated: 2026-03-29