
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
I am Kavya Garikapati, a 2025 Computer Science graduate with a strong interest in Artificial Intelligence, Machine Learning, and Data Science. I have a solid foundation in Python, SQL, Machine Learning, Deep Learning, and Data Analytics, developed through academic projects, research work, and continuous self-learning. My major project, Tomato Leaf Disease Detection using CNN and VGG16, involved applying transfer learning, data augmentation, model training, and performance evaluation techniques to build an effective disease classification system. This work was also recognized through an IEEE publication, reflecting my interest in research and innovation. I am proficient in Python and libraries such as NumPy, Pandas, and Matplotlib, with hands-on experience in data analysis and machine learning model development. I have also worked on projects involving medical image analysis and business intelligence dashboards, which strengthened my analytical and problem-solving skills. While my current knowledge of Artificial Intelligence is primarily based on fundamental AI, Machine Learning, and Deep Learning concepts, I am highly motivated to continuously learn and expand my expertise in emerging areas such as Generative AI, Large Language Models (LLMs), AI Agents, and intelligent automation. As a quick learner with a strong work ethic, I am seeking an entry-level opportunity where I can apply my existing skills, gain practical industry experience, and grow under the guidance of experienced professionals while contributing to impactful and innovative projects.
SRM University AP
B.TECH · CSE-AI&ML
August 1, 2021 – October 27, 2025
Tomato leaf disease detection using ml and dl
January 1, 2025 – May 1, 2025
Tomato Leaf Disease Detection Using Deep Learning is an agricultural AI project developed to identify and classify diseases in tomato plant leaves at an early stage, helping farmers take timely preventive measures and improve crop yield. The primary aim of the project was to build an accurate and automated disease detection system using Deep Learning and Transfer Learning techniques. In this project, I was responsible for data collection, image preprocessing, data augmentation, model development, training, evaluation, and comparative analysis. The dataset consisted of healthy and diseased tomato leaf images, which were preprocessed through resizing, normalization, and augmentation to improve model performance and generalization. I implemented a CNN model with VGG16 transfer learning and compared its performance with traditional machine learning algorithms such as KNN and SVM. The models were evaluated using accuracy, precision, recall, and F1-score metrics. A key achievement of the project was achieving high classification accuracy and demonstrating that deep learning models, particularly VGG16, significantly outperformed traditional machine learning approaches in disease identification. The results showed that the system could accurately detect multiple tomato leaf diseases, making it a practical solution for precision agriculture. As a future enhancement, the project can be expanded to support real-time disease detection through mobile or web applications, incorporate additional crop diseases, utilize advanced architectures such as ResNet or EfficientNet, and integrate IoT-based smart farming solutions for large-scale agricultural monitoring.
View ProjectChocolates sales dashboard using MSEXCEL[DATA ANALYSIS]
August 4, 2024 – September 5, 2024
Global Chocolate Sales Performance Dashboard using Excel is a business intelligence and data analytics project developed to analyze and visualize global chocolate sales data for effective decision-making. The primary aim of the project was to transform raw sales data into meaningful insights through an interactive and user-friendly dashboard. In this project, I was responsible for data cleaning, data preparation, KPI identification, dashboard design, visualization development, and business insights generation using Microsoft Excel. I utilized advanced Excel features such as Pivot Tables, Pivot Charts, Slicers, Conditional Formatting, Data Bars, and Interactive Dashboards to analyze sales performance across different products, salespersons, regions, and time periods. The dashboard was designed to answer key business questions, including total revenue generated, total boxes shipped, number of products sold, salesperson contributions, highest revenue-generating salesperson, top-performing regions, and best-selling products. A key achievement of the project was creating a comprehensive dashboard that provided real-time visibility into sales performance, shipment trends, and regional distribution through bar charts, pie charts, line charts, and KPI cards. The results enabled stakeholders to quickly identify sales trends, monitor performance metrics, evaluate top contributors, and make data-driven business decisions. As a future enhancement, the dashboard can be integrated with Power BI for advanced analytics, automated data refresh, predictive sales forecasting, and real-time reporting capabilities to further improve business intelligence and strategic planning.
View ProjectBrain tumor Detection using dl
June 4, 2023 – December 17, 2023
Brain Tumor Detection Using Deep Learning is a medical image classification project developed to assist in the early and accurate detection of brain tumors from MRI scans. The primary aim of the project was to leverage Artificial Intelligence and Deep Learning techniques to automate the tumor detection process and support healthcare professionals in diagnosis. In this project, I was responsible for data collection, image preprocessing, data augmentation, model development, training, evaluation, and result analysis. MRI images were preprocessed through resizing and normalization, and a Convolutional Neural Network (CNN) model was trained to classify images as tumor or non-tumor. The model was evaluated using performance metrics such as accuracy, precision, recall, and F1-score, achieving strong classification performance on the test dataset. A key achievement of the project was successfully demonstrating the effectiveness of deep learning in medical image analysis while improving model generalization through data augmentation techniques. The results showed that the system could accurately identify brain tumors from MRI images, highlighting its potential for real-world healthcare applications. As a future enhancement, the project can be extended to classify different types of brain tumors, incorporate advanced architectures such as VGG16 or ResNet, integrate explainable AI techniques, and be deployed as a web or mobile application to provide real-time diagnostic support for medical professionals.
View ProjectBCG X- Data Science Job Simulation
Forage
June 22, 2024 – Present
The candidate scored 35% on the Python Internship Test, indicating a foundational but weak grasp of the assessed Python skills, particularly in areas beyond basic syntax and data analysis.
Strengths
Limitations
Cultural Fit Analysis
The candidate's projects demonstrate an interest in applying AI/ML to diverse fields like healthcare and agriculture, indicating a willingness to explore different problem domains. The personal projects suggest a self-starter attitude. However, the lack of professional experience and a low technical score indicate that the candidate is not yet ready for a senior AI ML Engineer role. The candidate is currently pursuing a B.Tech in CSE-AI&ML, which aligns with the target role, but their experience level is '0', suggesting they are at an entry-level stage.
Soft Skills & Operational Fit
The candidate lists communication, leadership, problem-solving, time management, and creativity as professional skills. Project descriptions indicate an ability to work independently on defined tasks and a structured approach to problem-solving. However, the low technical test score suggests that practical problem-solving and technical execution need significant development for a senior role. The psychometric test score is 0, which means there is no data to evaluate logical reasoning, work attitude, stress handling, or team collaboration.