Roles and responsibilities:Data Pipeline Development: Collaborate with data engineers to build scalable data pipelines for model training and deployment, ensuring the continuous flow of clean, high-quality data.Data Visualization and Reporting: Create clear and concise visualizations to communicate complex data findings and model results to both technical and non-technical audiences.Team Leadership and Project Management: Led and mentored a team of data scientists and engineers, ensuring the successful execution of projects from conception to completion.Pipeline Creation and Optimization: Designed and implemented efficient data pipelines for various projects, overseeing the team's work to ensure timely and accurate delivery of results.Product Development for Augmentation Pipelines: Worked on product development focused on creating and optimizing data augmentation pipelines to enhance model accuracy and performance.

Data Collection and Preparation: Gather and clean data from various sources, ensuring it is ready for analysis. Handle missing data, outliers, and apply necessary transformations.Exploratory Data Analysis (EDA): Perform statistical analysis and visualization to understand data patterns, trends, and relationships that can inform model development.Model Development: Assist in building, testing, and refining machine learning models for predictive and classification tasks, using algorithms such as regression, decision trees, random forests, and neural networks.Feature Engineering: Identify key features that enhance model performance and create new features through data manipulation techniques.Model Evaluation and Optimization: Evaluate model performance using metrics like accuracy, precision, recall. Fine-tune models through hyperparameter optimization and cross-validation.Collaboration with Cross-functional Teams: Work closely with data engineers, software developers, and business teams to understand project goals, align on data needs, and deploy models.Documentation and Reporting: Prepare detailed reports and visualizations to communicate findings, model performance, and recommendations to both technical and non-technical stakeholders.Deployment and Maintenance: Assist in deploying models into production, monitor their performance, and update models as needed to maintain accuracy and relevance.Research and Continuous Learning: Stay updated with the latest advancements in data science techniques, tools, and technologies, and apply new approaches to improve existing processes.Projects:Cable Identification Project:Developed a classification model to identify 10 varieties of cables with visually similar features, achieving an accuracy of 99.7%.Deployed the solution using Python's Tkinter to create a user-friendly interface for easy operation and interaction.

As a data annotator, I have hands-on experience in labeling images using bounding boxes and polygons. I visited client locations to collect datasets, collaborated closely with data science teams, and wrote custom scripts to validate annotated data for quality assurance.I also developed a data validation app using Streamlit, which streamlined the process of tracking annotations, identifying errors, and facilitating quick corrections, enhancing overall data accuracy