Open to opportunities

Indu Nikhila Bhupati raju

@indunikhila7

Message

🎓 MCA Student | 💻 AI/ML Enthusiast | 🤖 Python | 🧠 Deep Learning | 📊 Data Analytics

India

Message

What I'm looking for

I seek an entry-level AI/ML role applying Python, ML and computer vision skills in a collaborative team focused on real-world impact, mentorship, and growth.

I am an MCA student deeply passionate about Artificial Intelligence and Machine Learning. I've built real-world projects like a Traffic Sign Recognition system using CNNs with 96% accuracy and a Virtual Finance Assistant that analyzes and predicts personal expenses using ML models.

My technical stack includes Python, scikit-learn, TensorFlow, Pandas, and OpenCV. I'm especially interested in applying AI to practical domains such as computer vision and financial technology.

I’m now seeking opportunities to grow as an AI/ML Engineer by working on real-time systems, solving meaningful challenges, and contributing to innovative products.

Experience

Work history, roles, and key accomplishments

AI-Powered Finance Assistant

Talent Trek

Jul 2025 - Present (11 months)

Collected and preprocessed financial transaction data and built classification models (Logistic Regression, Random Forest) to categorize expenses, improving handling of imbalanced classes and missing values for more robust predictions.

Python scikit learn Pandas Logistic Regression Random Forest data preprocessing Imbalanced Data Handling

Traffic Sign Recognition

Talent Trek

Jul 2025 - Present (11 months)

Developed a convolutional neural network for 43-class traffic sign classification on the GTSRB dataset, achieving 96% accuracy and implementing a robust image preprocessing and evaluation pipeline.

TensorFlow CNN Computer Vision Image Processing Model Evaluation Python

Imbalanced Data Classification

Sampath Info Tech

May 2024 - Present (2 years 1 month)

Addressed imbalanced classification by applying resampling techniques, tree-based ensembles and thorough evaluation (Precision, Recall, F1, AUROC), improving minority-class performance using Random Forests.