Aspiring Computer Vision and Machine Learning Engineer with a strong academic foundation in Computer Science (SGPA 7.5) and hands-on experience in developing and deploying real-time object detection models. Proficient in leveraging cutting-edge tools like Ultralytics YOLOv11, Roboflow, and PyTorch to achieve robust model performance (mAP 93.33%) and automate complex pipelines. Eager to apply expertise in building innovative and efficient AI solutions that drive real-world impact.
Computer Vision Engineer (Project)
Pune, Maharashtra, India
→
Summary
Led the development and deployment of real-time object detection models, enhancing system capabilities and operational efficiency within a research and development environment.
Highlights
Spearheaded the development and deployment of advanced object detection models utilizing Ultralytics YOLOv11, enabling real-time processing for critical applications.
Integrated Roboflow for comprehensive dataset management, including annotation, augmentation, and version control, significantly streamlining data pipelines and improving model training efficiency.
Optimized pre-trained YOLO models through fine-tuning on custom datasets, achieving specialized performance tailored to unique operational requirements.
Collaborated with cross-functional teams to successfully deploy optimized models on edge devices, leveraging GPU acceleration for enhanced real-time performance.
Executed extensive hyperparameter tuning and rigorous evaluation, achieving a mean Average Precision (mAP) of 93.33% to ensure exceptional model robustness and reliability.
Automated complex model training and evaluation pipelines using Python and PyTorch, substantially reducing manual effort and enhancing reproducibility of results.
Authored and published technical blogs and research on best practices for integrating Ultralytics and Roboflow into GPU-accelerated production environments.
Designed and developed a user-friendly interactive interface for YOLOv11 using Streamlit, enhancing accessibility and usability for end-users.
Trainee
Pune, Maharashtra, India
→
Summary
Contributed to enhancing office security and automation processes through the application of computer vision techniques during a focused training period.
Highlights
Integrated live camera feeds with Python to establish continuous monitoring and recognition of individuals, significantly enhancing office security in restricted zones.
Developed an automated object identification service using OpenCV, improving identification accuracy and streamlining processes during the development phase.
Implemented camera calibration and estimation techniques to optimize real-time recognition accuracy and strengthen access control systems.
→
Bachelor of Science
Computer Science
Grade: SGPA 7.5
Courses
Machine learning
OpenCV
Data structures
Java
Microsoft Office 365
Python
→
Board Exam
Intermediate
Grade: 76.66%
→
Board Exam
High School
Grade: 83.33%
Python, Java, C++, HTML, CSS, SQL, DBMS.
Ultralytics YOLOv11, Roboflow, PyTorch, OpenCV, Machine Learning, Object Detection, Hyperparameter Tuning, Model Deployment, Dataset Management, Real-time Applications.
VS Code, Google Colab, Streamlit, Visual Studio, Git, Version Control.
Data Structures, Algorithms.
POS Systems, Inventory Management, Customer Service.
→
Summary
Developed and managed an efficient restaurant item booking and billing system using C++ and Visual Studio, streamlining operations and enhancing customer experience through user-friendly interfaces for menu navigation, item selection, and table reservations.