Lost Word Finder
Applied NLP techniques including tokenization, lemmatization, and TF-IDF using NLTK and spaCy for text preprocessing and analysis. Designed a practical tool to aid word retrieval in language-based applications.
Project Trainee at Tata Communications
AI & ML Intern | Python • TensorFlow • NLP | Passionate about solving real-world problems with data
Tata Communications
10 mos · Hyderabad, Telangana, India
Assisted in end-to-end project development through research, documentation, planning, execution, and testing. Collaborated with cross-functional members to implement project tasks, troubleshoot issues, and deliver milestones within defined timelines.
Swecha Telangana
3 mos · Hyderabad, Telangana, India
Contributed to open-source projects, collaborated on community-driven initiatives, and gained hands-on experience
Suven Consultants and Technology Pvt.Ltd.
2 mos
I worked as an Ai Internwhere I developed and tested both supervised and unsupervised machine learning models using Python, TensorFlow, and Scikit-learn. My role involved data preprocessing, feature engineering, and exploratory data analysis on large datasets to improve model accuracy. I also assisted in model evaluation, NLP tasks, and contributed to end-to-end project documentation, ensuring smooth workflow and clear communication across the team.
Suven Consultants
February 2025 – March 2025 · Hyderabad
Preprocessed and transformed large datasets, performing feature engineering and text analysis using NLTK, spaCy, and NumPy. Developed and optimized machine learning algorithms using Python, Scikit-learn, TensorFlow, and Pandas for classification and prediction tasks.
Bachelor of Technology, Artificial Intelligence and Machine Learning
2022 – 2026
CGPA: 7.8/10
Intermediate, MPC
2020 – 2022
CGPA: 8.9/10
High School
2020
CGPA: 9.5/10
Applied NLP techniques including tokenization, lemmatization, and TF-IDF using NLTK and spaCy for text preprocessing and analysis. Designed a practical tool to aid word retrieval in language-based applications.
Conducted data collection and preprocessing, including text normalization, feature extraction, and noise reduction using Python, Pandas, and NLP libraries. Used Matplotlib and Seaborn to visualize features and trends in emotional and interaction-based data.
Enabled real-time, low-latency transmission of patient health data from medical devices to cloud platforms for continuous and personalized diabetes monitoring. Utilized cloud infrastructure to store, process, and manage large-scale healthcare datasets securely.