Piloted an internal chatbot system using Retrieval-Augmented Generation (RAG) with OpenAI and large language models (LLMs)Involved in the development of a predictive model to forecast customer repayment timeliness, enabling timely repayment reminders and saving 4 hours per day during the repayment cycle (days 1-5).Utilized classifier models, including Random Forest and XGBoost, to achieve accurate predictions and streamline the repayment reminder process.Applied data visualization techniques to communicate findings to stakeholders, heightening decision-making processes.Designed and implemented an L2 support framework, resulting in a 50% reduction in queue aging through efficient problem-solving.Identified and executed automation initiatives, leading to a 10% decrease in ticket influx and freeing up 2 hours/day for the L1 team.Compiled and presented weekly reports on top issues and key metrics (ticket aging, MTTR, tickets resolved) to provide insights for customer experience and product enhancements.

Collaborated with the data science team on a customer segmentation project, employing machine learning algorithms such as K-means clustering and hierarchical clustering to categorize customer data, enhancing personalized marketing strategies, and driving a 15% increase in customer engagementSpearheaded support for POS applications at the second-largest US home improvement retailer, leveraging Agile and user-centric design methodologiesImplemented Python3 automation for URL monitoring, leading to a substantial boost in team productivityDesigned real-time Splunk dashboards for proactive monitoring and rapid issue resolutionUtilized Rundeck to schedule proactive scripts, decreasing ticket inflow and enhancing system stabilityManaged incident tracking, analyzed and escalated critical production incidents, and developed dashboards and automated reports to uphold SLAs, ensure prompt issue resolution, and improve service capabilities.

Worked as a part of Incident and Problem management team.Provided quick work arounds that arise during peak sale hour.Escalating and communicating in a timely fashion the status of major incidents and problems with IT and business stakeholders including executive management.Liaison with Major Incident Managers (MIMs) to track high priority service related incidents and ensure root cause analysis and fault resolution is coordinated anddelivered to avoid recurrence of issues.Gained the SME level knowledge on RECEIVING - one of critical and productive applications in Retail stores.