Vikas yadav

AI/ML & GenAI Developer · Python · Machine Learning · NLP · LLMs · RAG

Navi Mumbai, Maharashtra, India

@vikas_yadav

GitHub LinkedIn

0 followers

🎓 B.Sc. Information Technology at Mumbai University · Graduating 2026

About

B.Sc. Information Technology graduate focused on Generative AI and Machine Learning, with hands-on Python projects across machine learning, NLP, and deep learning. Seeking AI/ML, GenAI, NLP, or Python internship opportunities.

Experience

Sales Data Entry

Handled sales-related data entry with attention to accuracy and consistency; gained practical experience in structured data handling and routine task execution.

Education

2026

B.Sc. Information Technology

Jnan Vikas Mondal College, Airoli

Information Technology · 2026

Information Technology

Skills

<3 months

SQL RAG LLMs NumPy Keras Python Pandas Seaborn Streamlit Matplotlib TensorFlow Embeddings Data Science scikit-learn Data Cleaning Random Forest Classification Decision Trees Model Evaluation Vector Databases Prompt Engineering Feature Engineering Recurrent Neural Networks Natural Language Processing Logistic Regression ( in progress )

Tools / apps / platforms

<3 months

Git GitHub VS Code Google Colab Jupyter Notebook

Projects

Titanic Passenger Survival Prediction ↗

Deep Learning, TensorFlow/Keras

Developed a deep-learning classification project to predict passenger survival using a TensorFlow/Keras neural-network workflow.
Movie Recommendation System ↗

NLP, Machine Learning, Python

Built a content-based recommendation system using movie genres, keywords, cast, crew and overview; applied text vectorization to identify similar movies.
Next word prediction ↗

Python,NLP, Streamlit

Built a machine-learning weather prediction project using Python and Streamlit with an end-to-end data preparation and prediction workflow.
Internship Readiness Predictor

Python, Scikit-learn, Streamlit

Built a classification application to predict internship readiness from structured candidate skill and preparation data. Performed data cleaning, EDA, train/test splitting and feature preparation; compared Logistic Regression, Decision Tree and Random Forest. Achieved 78.75% test accuracy with Logistic Regression; saved/loaded the model using Joblib and deployed an interactive Streamlit interface.

Explore the Broxer community

💬 Q&A Ask about roles, salaries and interviews — and help others. 👥 Circles Join discussions on skills, companies and industries. 📰 Feed Follow updates and insights from the community.