SHREYAS SHEKHAR
Contact Information
+91-9148862724 # shreyasshekhar98@gmail.com
ï LinkedIn Profile § GitHub Profile
Professional Summary
Final-year B.Tech student pursuing majors in Electronics and Communication Engineering at PES University
with a passion for software development, Data Analytics and cloud computing. Proficient in Python, Java, C++
and HTML along with expertise in full-stack development using web development frameworks like React,
Django, and Flask. Worked on databases like MySQL and MongoDB. Experienced in building scalable
applications and cloud infrastructure on AWS. Proficient in machine learning and data analytics tools like
Pandas, NumPy, Scikit-Learn, Tensorflow and OpenCV.
Education
PES University Bangalore, IN
Bachelor of Technology in Electronics and Communication Engineering October 2021 to July 2025 — CGPA: 6.35
• Relevant Coursework: Digital Image Processing, Artificial Neural Networks, Deep Learning, Cryptography,
Design of IOT Solutions, Ethical Hacking, Antenna Design, Digital Communication, Digital VLSI Design, Digital
Signal Processing, Control Systems, CADD
Deeksha PU College Bangalore, IN
12th Grade Science (PCMC) May 2019 to June 2021 — Percentage: 85%
Carmel School Bangalore, IN
10th Grade ISCE June 2018 to March 2019 — Percentage: 85%
Skills
Programming Languages: Python, Java, C++, HTML, CSS, JavaScript,
Software Development: React, Django, Flask, SDLC, REST API
Data and Databases: MySQL, MongoDB, RDBMS, Data Modelling, Query Optimization
Data Analysis: NumPy, Pandas, Seaborn, Matplotlib, Excel, PowerBI
Machine Learning: TensorFlow, Keras, Scikit-learn, OpenCV
Cloud: AWS (EC2, Lambda, S3, RDS)
Development Tools: Microsoft Azure AI, JIRA, Github, VS Code, Jupyter Notebook, PyCharm
Soft Skills: Analytical Thinking, Problem Solving, Communication Skills, Learning Agility, Business Acumen
Work Experience
WATSEMI TECNOLOGIES Bangalore, IN
Software Development Intern July 2024 - October 2024
• Collaborated with the team to design, deploy, and maintain cloud infrastructure using AWS, resulting in a 25%
increase in system reliability and a 40% improvement in scalability.
• Developed a Python application integrated with AWS services (EC2, S3, RDS) to automate inventory tracking and
reporting, leading to a 30% increase in operational efficiency and saving 15+ man-hours per week.
• Built a scalable ETL pipeline using AWS Lambda for real-time data processing and analytics, improving data
accuracy by 20% and reducing manual effort by 50%.
• Automated data extraction and transformation processes with Python scripts, minimizing human intervention by
80% and enhancing data processing speed by 50%
Projects
1. Smart Neck Band — MATLAB, Arduino GitHub Link
• Developed an IoT-enabled device that monitors cervical spine posture using ML algorithms, achieving
90% detection accuracy, delivering corrective alerts instantly, and reducing spondylitis risk by
30%.
• Processed over 1 million sensor data points to continuously refine the ML model, increasing system
reliability by 25% and enhancing posture awareness by 50%.
2. Customer Churn Prediction — Python, Keras, Jupyter Notebook GitHub Link
• Built binary classification models using Keras, achieving 75.62% validation accuracy through
hyperparameter tuning on 10,000+ customer records, boosting model performance by 15%.
• Enhanced customer retention strategies by 20% through advanced data visualization and reduced model
training time by 30% with optimized data pipelines.
3. Age and Gender Prediction — TensorFlow, Scikit-Learn, PyCharm GitHub Link
• Developed a system using pre-trained deep learning models to achieve 92% accuracy in age and
gender prediction from images and live video feeds, enhancing detection speed by 30%.
• Implemented real-time face detection with bounding boxes and labels, supporting photo upload and
webcam modes, improving user engagement by 40%.
4. Image Classification — TensorFlow, Keras, PyCharm GitHub Link
• Developed an image classification system using MobileNetV2, achieving 94% accuracy in object
recognition across 1,000+ categories, enhancing model efficiency by 25%.
• Enabled fast and accurate predictions with confidence scores, reducing image processing time by 30%
and improving user experience for real-time object detection.
5. Music Genre Classification — TensorFlow, Keras, Streamlit, PyCharm GitHub Link
• Built a deep learning model for classifying music tracks into 10 genres with 88% accuracy by
converting audio files into Mel spectrograms and leveraging a pre-trained CNN model.
• Developed an interactive Streamlit app, enabling real-time genre predictions with audio file uploads and
enhancing user engagement by 35%.
Certifications
Complete Data Science and Machine Learning Course (Udemy) Certificate Link
Microsoft Career Essentials in Data Analytics (Mirosoft) Certificate Link
Microsoft Azure AI Essentials (Microsoft) Certificate Link
Python, Django and HTML5 Course (Udemy) Certificate Link
Getting started with Storage (AWS) Certificate Link
Getting started with Databases (AWS) Certificate Link
Getting started with Compute (AWS) Certificate Link
Getting started with Serverless (AWS) Certificate Link
Getting started with CloudOPS (AWS) Certificate Link
Extracurricular Activities
Volunteer, Aatmatrisha - Assisted with stage setup and decorations for the PES University’s cultural fest Aatmatrisha.
Organiser, Kannada Club - Organized and coordinated Kannada events, promoting Kannada language and culture.
