About

I am deeply passionate about Artificial Intelligence and Machine Learning, with a strong interest in building intelligent systems that solve real-world problems. The ability to empower machines to learn, recognize patterns, and make predictions fascinates me and fuels my commitment to this field.

With hands-on experience in computer vision, deep learning, and real-time applications, I am focused on creating practical AI solutions—from fitness assessment tools to object detection systems. I strive to keep learning, innovate beyond limits, and contribute meaningfully to the evolving landscape of AI and ML.

What I’m currently learning and working on

  • machine learning icon

    Machine Learning

    Building scalable and efficient ML models to solve real-world problems and derive insights from data.

  • Deep Learning icon

    Deep Learning

    Applying CNNs and neural networks to solve complex tasks like handwritten recognition and satellite segmentation.

  • computer vision icon

    Computer Vision

    Developing intelligent vision-based systems for object detection, fitness tracking, and imagery analysis.

  • Technical knowledge icon

    Technical Knowledge

    I design and implement innovative AI projects by integrating technologies such as CNN, YOLO, U-Net, image segmentation, object detection, generative AI, and prompt engineering to deliver impactful real-world solutions.

Resume

Education

  1. JB Institute Of Engineering and Technology

    2021 — 2025

    B.Tech in Artificial Intelligence and Machine Learning | CGPA: 7.61

  2. Gayatri Junior College, Hyderabad

    2019 — 2021

    Intermediate XII in MPC | CGPA: 8.68

  3. Sri Gayatri e-techno School, Hyderabad

    2019

    Secondary Education | CGPA: 9.0

Work Experience

  1. Computer Vision Engineer (Remote) | Digital Bot Solutions Pvt. Ltd. (UK-based)

    Project: AI Smart Restaurant Monitoring System | Aug 2025 – Dec 2025

    • Designed and deployed a production-grade AI-powered real-time restaurant monitoring system using YOLOv8 for multi-class object detection (customers, waiters, staff, food), achieving 75.1% mAP@0.5 with 79.2% precision.


    • Built end-to-end cloud infrastructure on AWS EC2 (g4dn.xlarge with Tesla T4 GPU), achieving 15-20 FPS real-time inference with 43ms latency per frame.


    • Implemented multi-threaded pipeline architecture with DeepSORT tracking, zone-based spatial reasoning, and custom rule engine for table state management and event generation.


    • Developed React dashboard with real-time MJPEG streaming, live analytics, and integrated Flask REST API with AWS DynamoDB (6 tables) for event storage and retrieval.


    • Skills: Python, YOLOv8, TensorRT, DeepSORT, OpenCV, PyTorch, AWS (EC2, DynamoDB, S3, Lambda, EventBridge), Flask, React, Nginx, RTSP/MJPEG Streaming, Multi-threading.

  2. Machine Learning Developer Intern | Tenali's Sports Tech Pvt. Ltd

    Project: Fitness Assessment Training using AI | May 2024 – Aug 2024

    • Built a computer vision-based system using OpenCV and MediaPipe to analyze over 100+ live videos of real-time supported exercises (Bicep Curls, Squats, Pushups, Planks).


    • Achieved 30% improvement in posture accuracy and automated real-time rep counting and weekly performance reporting through automated email sending system.


    • Skills: Python, OpenCV, MediaPipe, Pose Estimation, Automation, Machine Learning.

Projects

  1. Voice-Vision-Hand Controller Mouse

    April 2025 – April 2025

    • Developed a smart desktop controller using eye tracking, voice commands, and hand gestures to replicate all mouse functions—like left/right clicks, double-clicks, and full desktop navigation—via gaze control, voice-based app launching, and index finger cursor movement.


    • Trained using LSTM model Architecture on eye movement data to improve accuracy and smooth interaction.


    • Achieved over 80% precision in real-time operation across varied environments.


    • Skills: Python, LSTM, OpenCV, MediaPipe, Dlib, Speech Recognition, Eye-Tracking, Hand Tracking, Voice Automation, Facial Landmark Detection, Human-Computer Interaction, Deep Learning.

My skills

  • Python
    85%
  • Machine Learning/Deep Learning
    80%
  • Computer Vision (OpenCV, YOLO, DeepSORT)
    90%
  • Cloud & DevOps (AWS, Docker, Nginx)
    75%
  • Frameworks (TensorFlow, PyTorch, FastAPI)
    80%
  • Object Detection & Tracking (YOLOv8, TensorRT)
    85%
  • Real-time Video Processing & RTSP Streaming
    80%
  • Generative AI & Prompt Engineering
    70%

Publications & Research

  1. LeYOLO: A New Scalable and Efficient CNN Architecture for Object Detection – IJETRM (Publication)

  2. Fitness Assessment Vision with AIML: AI-powered workout tracking using OpenCV. (Research)

Certifications