Worked on an RLHF (Reinforcement Learning from Human Feedback) pipeline focused on dataset creation, data annotation, and model evaluation. My role involved designing and curating high-quality prompt datasets, reviewing AI-generated responses, and providing structured feedback based on accuracy, relevance, safety, and helpfulness. Contributed to improving model performance by ensuring consistent evaluation standards and high-quality human feedback for training alignment and refinement.
An anomaly detection system for EV battery telemetry data using machine learning. The project identifies abnormal patterns in battery data to support early fault detection and predictive maintenance.
0
33
Diabetes Prediction System
Developed a prediction system using Pima Indians dataset, achieving 84% accuracy with Random Forest. Performed comprehensive data cleaning and median imputation for missing values. Implemented feature scaling and model evaluation with cross-validation.
84% Accuracy Data Cleaning Feature Scaling
Technologies
Python Scikit-learn Pandas Random Forest