Skills

Programming

PythonSparkPySparkMicrosoft SCOPE

Query Languages

SQLPySparkSCOPE (ADLA)

Big Data & Cloud

Apache KafkaSpark Structured StreamingDatabricksAzure Data Lake (ADLS Gen2)Delta LakeADLACosmos

ML Frameworks

TensorFlowScikit-learnNLTK

Data Visualization

Power BIMS ExcelSeabornMatplotlib

Statistical Analysis

Hypothesis TestingRegression AnalysisEDATime Series Analysis

Markup

HTML

Experience

  1. Data Analyst · Analytics Consulting Firm

    November 2024 – Present

    Chennai — Subscription & device-engagement analytics for a global gaming & entertainment platform

    • Built large-scale distributed data pipelines using Microsoft SCOPE on ADLA and Cosmos clusters to process millions of subscription and device telemetry records.
    • Engineered end-to-end subscription lifecycle analytics across first-party and partner subscription services — acquisitions, renewals, cancellations, expirations and SKU-level conversions.
    • Developed bundle conversion logic from event and subscription datasets to track partner-service users converting to the premium subscription tier across multiple SKUs and recurrence IDs.
    • Built month-over-month acquisition, retention and conversion reports supporting monetization strategy and subscriber growth decisions.
    • Designed device reactivation analysis identifying inactive devices returning to active usage, with inactivity periods from 1 to 6+ months.
    • Analyzed Monthly Active Device (MAD) and rolling active-device metrics by integrating usage, application and revenue datasets into consolidated engagement views.
    • Applied deduplication (ARGMAX, aggregation) and query optimization to improve performance and accuracy on large-scale distributed SCOPE queries.
    • Completed company boot-camp training and earned the Databricks Data Engineer Associate certification (93.2%) during onboarding (Nov 2024 – Apr 2025).

  2. Project Intern · Analytics Firm

    August 2023 – September 2023

    Bengaluru

    • Built a Retrieval-Augmented Generation (RAG) chatbot using Generative AI to answer queries from uploaded documents.
    • Developed an NLP-based document summarization bot to extract and condense product review content.

Projects

Financial Fraud Detection Pipeline

January 2025 – March 2025
  • Built a real-time fraud detection system ingesting streaming transactions via Apache Kafka and processing them with Spark Structured Streaming on Databricks.
  • Designed a Medallion architecture (Bronze → Silver → Gold) for transformation, quality control and storage using Delta Lake.
  • Applied SQL-based anomaly detection and rule-based logic to flag suspicious transactions, with a Power BI real-time monitoring dashboard.
  • Configured automated email alerting for high-risk transaction events.
DatabricksApache KafkaSpark Structured StreamingDelta LakePower BISQLPython

University Knowledge Graph

December 2023 – April 2024
  • Designed an ontology representing university entities (faculties, research papers, schools, departments) and populated a knowledge graph using SPARQL and RDF.
  • Queried and benchmarked multiple LLMs on the knowledge graph to evaluate retrieval accuracy and response quality.
  • Optimized SPARQL queries and data representation to improve retrieval accuracy and response time.
SPARQLRDFKnowledge GraphsLLMs

Movie Genre Prediction

November 2022 – January 2023
  • Preprocessed movie plot data using NLP techniques (tokenization, stemming, TF-IDF) and built a multi-label classification model to predict genres.
  • Evaluated multiple supervised and unsupervised algorithms on accuracy, precision, recall and F1-score; tuned hyperparameters to reduce overfitting.
PythonNumPyPandasScikit-learnNLTKMatplotlib

Achievements

  • Cultural Fest Team Coordinator — led the CSE department team to win the University Cultural Fest (2023).
  • Author of technical articles on Large Language Models published on Medium.