About

I strongly believe that magic happens at the intersection of multiple fields.

I am deeply enthusiastic about working at the intersection of medicine and artifical intelligence. I’m a full stack developer who’s deeply enthusiastic about using Convolutional Neural Networks to perform diagnosis and prognosis of healthcare usecases like breast cancer detection, Alzheimer’s prediction, pre-term birth.

I’ve worked upon various ML use cases in the financial domain and I feel I'm ready to dive into the world of Medical-AI.

Interests

Software Development

Machine Learning

Computer Vision

Natural Language Processing

Software Engineering

Visualization

Algorithms

Image Processing

Education

B.E. in Information Technology

July 2014 - June 2017
Relevant Coursework
  • Intelligent Systems
  • Image Processing
  • Data Mining & Business Intelligence
  • Big Data Analytics
  • Data Structures & Algorithms
  • Database Management Systems

Online Certification

Relevant Courses
  • AI in healthcare specialization
  • Fundamentals of Machine Learning for Healthcare
  • Evaluations of AI Applications in Healthcare
  • AI in Healthcare Capstone
Relevant Courses
  • Deep Learning Specialization
  • Neural Networks and Deep Learning
  • Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization
  • Convolutional Neural Networks

Experience

J.P Morgan Chase & Co

August 2017 - Present

Associate Vice President

  • Developed a reinforcement model to train, evaluate and tune a 3-layer convolutional neural network controlling a virtual 1/18th scale race car; achieved a lap time of 6 secs, securing 1st rank at the firm-wide AWS Deepracer Championship League of 2021.
  • Built a CNN model based on the VGG-16 architecture to perform signature comparison thus, detecting check frauds; achieved accuracy of 96% for American and 95% for European signatures.

Software Associate

  • Developed a python chatbot using RASA framework to retrieve the client account details instantly, thus reducing the manual work by 75%.
  • Modernized architecture by Introduction of CICD pipeline (using JULES), Cassandra Reactive Programming, adoption of a centralized RESTful microservices based architecture, and undertaking JDK upgrade.
  • Spearheaded Agile Transformation for 100+ members global team. Prioritized Project delivery by leading as Scrum Master.
  • Mentored 200+ freshers to build sustainable AI solutions for NGOs as an expert programmer at Code for Good program.

Technology Analyst

  • Built a machine learning model with an accuracy of 98% using Random Forest Classifier algorithm and XGBoost to measure and monitor the customer churn rate.
  • Developed a global strategic performance platform for best in class robust calculations, attributions & performance analytics to decommission a vendor product saving the firm $1.8B annually.
  • Automated testing by implementing a Regression Testing framework using Gherkins and hence bridged the gap between business and development using BDD, reducing manual work by 200%.
  • Undertook cloud adoption and implemented a spring-boot api service as a gateway between a JP Morgan internal cloud platform and AWS for seamless data transfer.

IndiaShield

April 2021 - Present

Founding Member

  • INDIASHIELD is one of the largest COVID-19 emergency response efforts in India. The network of Life Savers has serviced over 48,000 requests in a short span of 22 days and helped save numerous lives during the harsh second wave of COVID-19 in India. Over 400 volunteers work 24/7 to cater to requests by any help-seeker coming to our support group on support.indiashield.in
  • Developed a python bot to scrape tweets comprising available covid resources like oxygen, ICU beds, plasma etc; integrated it with AWS; enabled dynamic API calls with the help of Amazon API Gateway, AWS Lambda, and DynamoDB to store data and update covid website (https://warwithcovid.club/) on runtime, thus helping 100k+ Indian citizens meet urgent needs.

Projects

COVID-19 Twitter Bot

Brain Tumor Segmentation

AWS Deepracer League

Preterm Birth Detection

Face Recognition

YOLO Object Detection

Transfer Learning

U-Net Image Segmentation

Skills

Languages and Databases

vectorlogo.zone vectorlogo.zone vectorlogo.zone upload.wikimedia.org vectorlogo.zone vectorlogo.zone

Frameworks

vectorlogo.zone vectorlogo.zone vectorlogo.zone vectorlogo.zone vectorlogo.zone vectorlogo.zone vectorlogo.zone upload.wikimedia.org

Tools

vectorlogo.zone vectorlogo.zone vectorlogo.zone vectorlogo.zone

Contact

Social Profiles

Email

kandarkarsayali@gmail.com

sayali.kandarkar@somaiya.edu