Highly versatile Computer Science graduate specializing in Data Analytics and Machine Learning, adept at transforming complex datasets into actionable insights. Proficient in SQL, Python, Power BI, and Tableau, with proven experience in building predictive dashboards and defining key performance indicators. Skilled in Exploratory Data Analysis and leveraging cloud-native tools like AWS Glue, S3, and Airflow to automate data preparation. Seeking to apply data expertise to drive impactful performance improvements and data-informed decision-making in a challenging environment.
Full Stack Developer & Cloud Database Administrator
San Jose, CA, US
→
Summary
Administered and maintained PostgreSQL databases on AWS RDS, developing Python-based microservices and implementing robust security measures to enhance data quality and scalability.
Highlights
Administered and optimized PostgreSQL databases on AWS RDS (Virginia & Ireland), enhancing data accessibility by 25% and ensuring high availability, automated security, and audit compliance.
Investigated and resolved critical database issues, including schema conflicts and table visibility problems, reducing system downtime and support requests by 40% in a scrum-based development environment.
Developed and maintained Python-based microservices with predictive data modeling and RESTful APIs, improving data accuracy by 20% and boosting backend efficiency and scalability in centralized PostgreSQL.
Implemented S3 bucket policies and encryption settings to ensure compliance with data security standards, automating alerting and compliance checks using AWS Lambda and SNS.
Contributed to CI/CD migration planning by designing automated deployments from GitHub to AWS across environments to improve consistency and reduce deployment errors.
Student Supervisor-Data Analyst
Milwaukee, WI, US
→
Summary
Led a staffing optimization project and developed data-driven dashboards, significantly improving workforce efficiency and reducing operational costs.
Highlights
Led a staffing optimization project utilizing business analysis and capacity planning on POS data and Excel, improving workforce efficiency by 55% and reducing operational imbalance.
Created recurring Excel dashboards with PivotTables, charts, and VLOOKUPs to monitor inventory usage, automating weekly supply ordering and saving 1.5+ hours of manual effort per week.
Built prescriptive, ETL-style dashboards by transforming raw POS logs into actionable insights, enabling data-driven decisions that reduced inventory overstock by 20%.
Student Data Analyst
Hyderabad, Telangana, India
→
Summary
Conducted detailed analysis of CT scan datasets, developed predictive modeling workflows, and designed clinician-facing dashboards to support early detection and real-time inference.
Highlights
Conducted detailed analysis of CT scan datasets to identify diagnostic patterns across normal, benign, and malignant classes, supporting early detection through advanced data wrangling and statistical profiling.
Built end-to-end predictive modeling workflows using Python and OpenCV for clinical image preprocessing, achieving a 22% reduction in overfitting via targeted data augmentation techniques.
Designed and delivered clinician-facing dashboards and reports using Power BI and Tableau, validated across three medical institutions with over 90% positive feedback on diagnostic clarity and system responsiveness.
Deployed analytics outputs using serverless architecture (AWS Lambda + S3), enabling real-time inference with sub-2-second latency and ensuring alignment with clinical KPIs on speed and reliability.
Data Science and Analytics Intern
Pune, Maharashtra, India
→
Summary
Developed predictive and prescriptive analytics models, transformed patient datasets, and delivered interactive dashboards to improve clinical decision-making.
Highlights
Built predictive & prescriptive analytics models using Decision Tree and KNN on 900+ patient records with R and Seaborn, achieving 81.9% test accuracy and improving early heart disease detection by 35%.
Transformed structured patient datasets using Pandas and SQL, reducing preprocessing time by 30%, and centralized curated data in AWS S3 for scalable access within a structured, phase-based workflow.
Performed feature importance analysis to identify top KPIs such as chest pain type and max heart rate, enabling model refinement and boosting accuracy.
Delivered interactive dashboards via Tableau and Power BI integrated with AWS Athena, enabling proactive clinical decision-making, identifying 15% more critical cases, and reducing manual data retrieval by 40%.
Query Administrator
→
Summary
Created and maintained reusable queries and stored procedures to support recurring reporting for Youth and Transfer programs, ensuring output accuracy and alignment with business logic.
Highlights
Developed and maintained robust reusable queries and stored procedures, ensuring accurate and business-aligned reporting for Youth and Transfer programs.
Public Health Data Analyst – Senior NSS Volunteer
→
Summary
Led ward-level data collection, organized service camps, and spearheaded rural infrastructure projects to improve public health and community engagement.
Highlights
Led ward-level data collection and validation using Excel and SSIS for public health awareness and screening drives, improving follow-up accuracy and increasing insurance scheme participation by 25% through data-informed targeting.
Organized and executed 32+ service camps using insights from health reports and survey data, leveraging Excel pivot tables and filters to stratify outreach by age, gender, and risk, enabling effective and targeted community engagement.
Spearheaded rural infrastructure projects in four villages, mobilizing volunteers through data-driven planning models to support Clean India campaigns, sanitation and sustainable waste management.
→
Master's
Computer Science
→
Bachelor of Technology
Computer Science
Issued By
Microsoft
Issued By
Coursera (University of Michigan)
Issued By
Internshala
Issued By
Knowledge Solutions (India)
Issued By
Issued By
Python (Pandas, NumPy, Scikit-learn, Seaborn, Matplotlib, Plotly), R (dplyr, ggplot2), SQL, C, C++, Java, Spring Boot, HTML, CSS.
Scikit-learn, TensorFlow (Keras), BERT, Hugging Face Transformers, OpenCV, RESTful API.
AWS (Cognito, Glue, Athena, Lambda, SageMaker, QuickSight, CloudWatch, API Gateway), Apache Airflow, Kafka, Docker, ETL Pipelines, SSIS.
Excel, Google Sheets, Power BI (Dashboards, Interactive Reports), Tableau.
Git (Version Control), GitHub, CI/CD (GitHub Actions), Figma, R Markdown.
Jupyter Notebook, Google Colab, VS Code, R Studio, Microsoft Excel, Microsoft Access.
MySQL, PostgreSQL (AWS RDS – multi-region), AWS S3.
Summary
This project involved building a public health data pipeline using AWS Glue and S3 to process large datasets, applying K-Means clustering and prescriptive analytics to uncover disparities, and automating reporting with Apache Airflow to create dashboards in Amazon QuickSight and Power BI.
Summary
This project focused on enhancing grayscale image datasets using adaptive CLAHE with optimized clip-limits, evaluating enhancement quality with KPIs, curating datasets for ML workflows, and visualizing pixel intensity distributions for quality assurance.
Summary
This project involved building a sentiment classification pipeline on 20,000+ tweets using BERT-based NLP models, applying clustering for sentiment categorization, improving model performance through data quality, and managing versioned datasets in AWS S3.