Ashwini Vittalsa Shingri

Computer Science Engineering graduate · Machine Learning and Software Engineering

Gajendragad, Karnataka, India

@shingri_ashwini

0 followers

About

Computer Science Engineering graduate with a strong foundation in problem-solving, software engineering, and applied machine learning. Experienced in building computer vision pipelines, backend web services, and data models using Python.

Experience

Artificial Intelligence & Machine Learning Intern

Dyashin Technosoft Pvt. Ltd. · Bengaluru, India

Feb 2026 – May 2026

Built, trained, and deployed predictive machine learning and CNN models with interactive RESTful web endpoints using Flask. Engineered an end-to-end Employee Retention & Churn Prediction analytics pipeline to evaluate HR metrics and identify attrition patterns. Designed and evaluated a specialized CNN medical imaging pipeline to detect liver cancer patterns from CT scan data.

Education

B.E. in CSE

AGM Rural College of Engineering and Technology · Visvesvaraya Technological University

Computer Science · Dec 2022 – May 2026
Pre-University Course (PUC, Science)

Prerana PU Science College

Science · 2019 – 2021
SSLC (10th Standard)

Shri V. T. Raibagi English Medium High School

2019

Skills

3 to 6 months

Python Machine Learning API Integration Understanding

<3 months

SQL CSS Oop HTML NumPy Flask Keras Pandas OpenCV TensorFlow scikit-learn Data Structures and Algorithms

Tools / apps / platforms

<3 months

Git Linux GitHub VS Code

Projects

Secure Real-Time Chat Application

Python, WebSockets, Cryptography

Developed a real-time messaging application incorporating robust end-to-end encryption using modern cryptographic algorithms. Implemented secure key exchange protocols and user authentication workflows to ensure strict message confidentiality and user integrity. Designed a responsive, intuitive interface delivering low-latency, reliable communication across connected clients.
LIVision – Liver Cancer Detection from CT Scans

Python, OpenCV, CNN, Flask

Engineered a deep learning system to process abdominal CT scan images and accurately classify liver cancer cases. Implemented thresholding, contour detection, and Histogram of Oriented Gradients (HOG) feature extraction to isolate regions of interest. Trained and fine-tuned a CNN classifier, improving detection performance on preprocessed medical imaging datasets.

Explore the Broxer community

💬 Q&A Ask about roles, salaries and interviews — and help others. 👥 Circles Join discussions on skills, companies and industries. 📰 Feed Follow updates and insights from the community.