Gelli Tarun

Building and optimizing ML models for credit risk, fraud detection, and customer segmentation. Designed and deployed end-to-end AI/ML solutions by engineering scalable PySpark data pipelines, building predictive models, and delivering actionable insights through advanced analytics. Implementing end-to-end ML pipelines, including data preprocessing, feature engineering, and model training. Monitoring and maintaining models in production, retraining as needed for performance. Collaborating with engineering teams to integrate models into scalable systems. Utilizing SQL for extracting and transforming large datasets from financial databases to support model development. Optimizing PySpark notebooks and SQL queries to improve data processing efficiency and ensure seamless integration with ML pipelines. Built working models of: PRIME AI, Sales Process Hubspot Funnel, Seamless ML Pipelines Migration with AutoML for Drift Detection and Monitoring, Studio Looker, Top Up Scoring Model, Digital Footprint.

Building AI models. Built working models using deep learning (neural networks and ANN's). Explaining the usefulness of the AI models to a wide range of individuals within the organization, including stakeholders and product managers. Developing infrastructures for data transformation and ingestion. Applied data science techniques, such as machine learning and statistical modeling. Experienced project manager with a track record of successful planning, execution, and team collaboration, adept at risk management and maintaining rigorous quality assurance processes. Built working models of: Chatbot Using Generative AI, Health diseases (heart attack prediction), Health of Lung Infection (CNN with PyTorch and Opencv), Predictive Modeling (US betting firm), Health Diabetic Retinopathy (CNN with Opencv and TensorFlow Serving), Stock Price Prediction (RNN + LSTM, AI Pipeline).