Led the development of a Skin Cancer Classification model using ResNet50, a deep convolutional neural network, to identify melanoma from dermoscopic images.Performed extensive image augmentation techniques (e.g., rotation, flipping, zooming) to prevent overfitting and improve the robustness of the model.Conducted error analysis on misclassified images, providing insights that helped in refining the model’s performance.Published a report detailing the approach and findings, which was later shared with academic and professional communities through AI research forums.Enhanced teamwork and cross-cultural collaboration through regular communication with supervisors and peers from diverse backgrounds, refining global project management skills.

Engaged in an AI-focused internship, developing knowledge in machine learning algorithms, neural networks, and natural language processing.Collaborated with a team to develop an AI-based predictive model that enhanced customer support systems, reducing response times by 20%.Gained experience in applying algorithms like decision trees, SVMs, and k-means clustering for real-world applications.Worked with datasets to identify trends and patterns, improving the predictive accuracy of the models by fine-tuning hyperparameters.Presented a capstone project that simulated AI-based solutions for network optimization to senior NTI experts.

Conducted in-depth analysis on construction site data to identify key metrics for efficiency improvement.Developed and maintained dashboards using Power BI to visualize data trends, enabling better decision-making for project managers.Automated manual data entry tasks by writing Python scripts, reducing the time spent on data processing by 25%.Conducted A/B testing on operational data to determine optimal resource allocation, which improved material usage efficiency by 10%.Collaborated with engineers to define requirements for data collection, ensuring the accuracy and reliability of data for critical business decisions.