Welcome to my GitHub profile! I am a skilled Software Engineer specializing in Computer Vision, with a focus on object detection, tracking, and motion planning. I hold a Master's degree with distinction in Cybersecurity and Artificial Intelligence from the University of Sheffield, England.
-
Founding Engineer-Machine Learning - Idea Enterprises
• Curated Custom Dataset combining Open Source Datasets, Sources and proprietary data
• Finetuned Pre-trained Object Detection and Action recognition Models on Custom Dataset using Distributed Data Parallel Training Approach with high Top-1(87%) Top-5 Accuracy(95%), and F-1 Score(91%)
• Built End to End low latency(<1s) inference pipeline for real time system with high throughput(25 cctvs per node) for action recognition in CCTV videos
• Deployed system using Nvidia Deepstream and Apache Kafka, integrating with Front-End Application providing Realtime Monitoring and Alerts. -
Graduate Teaching Assistant - University of Sheffield
Supporting students in Big Data Analytics, Database Design, and Data Modelling using tools like Databricks, AWS, SQLite, and Python. -
Software Engineer - Swig Solutions, India
Designed and developed responsive, user-friendly web applications tailored for diverse client needs. -
Industrial Trainee - Codeburnerz Technologies, India
Contributed to the development of a School Management System.
-
M.Sc. Cybersecurity and Artificial Intelligence - University of Sheffield
- Grade: Distinction
- Modules: Scalable Machine Learning, Natural Language Processing, Text Processing, Cyber Threat Hunting, Secure Software Development.
-
B.Tech. Computer Science - Maharshi Dayanand University
- Modules: Neural Networks, Web Development, Database Management Systems, Compiler Design.
-
Football Analysis Using Computer Vision
This project analyses football matches using advanced computer vision techniques, including YOLO for object detection (players, ball, referees), ByteTrack for tracking movements, and KMeans and SigLip for team classification. -
Neural ODEs for Domain Wall Analysis
Developed models to analyze copper nano wire domain walls under oscillating magnetic fields using Neural ODEs and compared results with RNNs and LSTMs.
Tech Stack: Python, PyTorch, TensorFlow. -
Facial Recognition Neural Networks
Contributed to CNN-based facial recognition systems utilizing Python, OpenCV, and dlib.
