Hire Himanshu T. - LLM Engineer

* Engineered and optimized 100 * prompts and responses for diverse applications, enhancing AI accuracy by 30%. * Conducted fact-checking and validation to ensure 95% * accuracy across multiple domains. * Implemented contextual fine-tuning strategies, improving coherence and relevance of AI-generated content.

* As a Data Analyst Intern at E&ICT IIT Guwahati, I gained hands-on experience in data analytics, data visualization, and business intelligence. This internship focused on leveraging Excel and Power BI for data-driven decision-making.Key Learnings & Contributions: * Developed skills in data cleaning, transformation, and statistical analysis using Excel. * Created interactive dashboards and reports using Power BI to visualize key business insights. * Learned Power Query, DAX functions, and data modeling for efficient data processing. * Worked on real-world datasets, applying business analytics techniques to derive insights. * Improved my ability to present and interpret data for effective decision-making.This internship strengthened my analytical thinking and provided me with practical experience in handling and interpreting data for business use cases.

* Task 1: Iris Flower ClassificationMy first task was creating an Iris flower dataset classification model. The goal was to build a model capable of classifying different types of iris flowers based on features such as petal length and width.Task 2: Image to Pencil SketchFor the second task, I worked on converting images into pencil sketches using image processing techniques. This project involved transforming a regular image into a grayscale sketch, mimicking the appearance of hand-drawn art.Task 3: Next Word Prediction ModelIn this task, I built a model capable of predicting the next word in a sentence. This task was more challenging as it required natural language processing (NLP) techniques and the use of recurrent neural networks (RNNs) or Long Short-Term Memory (LSTM) models.Task 4: Handwriting Digit RecognitionThe final task focused on developing a handwriting digit recognition model using the MNIST dataset. This dataset consists of images of handwritten digits (0-9), and the aim was to classify them correctly.