● Helped streamline research operations for 10+ faculty by building internal tools that improved data flow and document tracking, reducing manual tasks by 40%. ● Designed a scalable database system with 18+ normalized tables on Azure SQL and implemented B+ Tree indexing to support fast, reliable queries. ● Built a menu-driven Java application using JDBC, enabling users to manage and update records with ease across 4 core data modules. ● Used LLM APIs and FAISS to automate analysis of 1,000+ academic papers, indexing over 20,000 content chunks for fast and relevant retrieval. ● Analyzed 990,000+ health records to predict smoking and drinking behavior using XGBoost, achieving 73% accuracy for drinkers and 69% for smokers. ● Finished 2nd in a university Kaggle challenge by developing an XGBoost model for hospital readmission prediction, with 64.1% accuracy and actionable risk insights. ● Modeled online retail revenue using MARS regression on customer session data, achieving an RMSE of 0.626 and R² of 0.777 through log transformation and feature engineering. ● Set up real-time monitoring dashboards in Grafana that tracked 100% of API traffic, cutting issue resolution time by 35%. ● Automated deployments with GitHub Actions, reducing update time by 70% and improving team workflow stability. ● Provided hands-on support to 50+ platform users and ensured full compliance with university privacy policies when handling sensitive data. ● Contributed to data analytics tasks including EDA, statistical testing (ANOVA, t-tests), and ML model evaluation across 5+ healthcare and behavioral datasets. ● Developed CareerCompass, a faculty-support tool that analyzes student resumes against job descriptions using LLaMA 3, spaCy, and SentenceTransformers to identify strengths and skill gaps. ● Enabled automated ATS scoring, keyword match insights, and JD scraping, helping departments streamline student shortlisting for campus job postings.

● Contributed to INFOROS, Infor’s internal operating system used by 10+ enterprise teams, gaining hands-on experience across modules like API, ION, Data Lake, and Process Intelligence throughout the full SDLC. ● Built real-time dashboards in Sumo Logic and Grafana that helped the team catch and resolve 80% of production issues before clients ever noticed, greatly improving system reliability. ● Took ownership of ~80% of assigned Jira tickets, including several high-impact production issues, and ensured timely fixes during tight deployment cycles. ● Automated key QA workflows using Postman and JavaScript, cutting down manual testing time by 40% while improving the accuracy of Automated testing and integration testing. ● Used tools like Splunk, AWS, Azure, and Postman to troubleshooting and code review bugs to improve performance ultimately reducing average issue resolution time by 30%. ● Helped end to end monthly production deployments, reducing downtime by 25% and making rollout cycles smoother for both cross functional teams and end users. ● Actively participated in Agile sprints, collaborating with developers, QA engineers, and DevOps to plan, test, and ship features on schedule. ● Wrote and optimized 25+ SQL queries to support backend analytics and ETL workflows, performance monitoring, and client-facing metrics. ● Authored over 10 technical documents on system components like APIs and ION workflows, making it easier for new team members to ramp up quickly. ● Worked closely with SRE and DevOps teams to improve observability, helping maintain 99.9% uptime across cloud deployments. ● Completed certifications in Sumo Logic Fundamentals and Search Mastery, deepening my skills in log analytics, monitoring, and incident response.