Los Angeles Machine Learning

Harshada Santosh Jadhav

Los Angeles, CA +1-323-***-**** # ***************.****@*****.*** ï Harshada Jadhav EDUCATION

California State University, Los Angeles Aug 2023 – May 2025 Master of Science in Computer Science GPA: 3.55/4.0 Savitribai Phule Pune University, Pune July 2017 – April 2021 Bachelor of Engineering in Computer Engineering GPA: 3.85/4.0 EXPERIENCE

Abzooba India Infotech Pvt. Ltd. June 2021 – June 2023 Big Data and Cloud Junior Developer (40 hours/week) Pune, Maharashtra, India

• Worked on a comprehensive end-to-end ETL pipeline leveraging AWS services, including Glue, RDS, S3, Lambda, Athena, OpenSearch, and EC2 to speed up data processing processes for 100 GBs of data using Python and PySpark.

• Improved data analysis capabilities using Microsoft Suite, allowing the organization to make data-driven decisions for handling 1-5 billion records and identifying significant business insights.

• Optimized ETL processes by implementing advanced techniques, debugging, and backtracking within a CI/CD framework, resulting in a 40% reduction in data processing time and a 25% increase in overall data accuracy.

• Analyzed datasets in PySpark, transforming complex nested JSON, text, and CSV files into actionable insights for stakeholders. Delivered actionable insights, enabling data-driven decision-making while following Agile development methodology.

• Used Shell scripting to automate EC2 operations, reducing manual tasks and improving deployment speed. SKILLS

• Programming & Scripting: Python, SQL, PySpark, Shell Scripting, Java (Basics)

• Data Engineering & ETL: AWS (Glue, Lambda, RDS, S3, EC2), Apache Spark, Airflow (familiar), Databricks (familiar)

• Cloud Platforms: AWS, Azure (basic), Snowflake (familiar)

• Data Analytics & BI: Power BI, Tableau, Dash Framework, Data Cleaning, Transformation, JSON/XML Parsing

• Databases: PostgreSQL, MySQL, SQL Server, AWS RDS, Stored Procedures

• DevOps & Workflow: Git, GitHub, GitHub Actions, CI/CD, Agile (Scrum)

• Machine Learning: scikit-learn, Pandas, NumPy, Regression, Classification, Clustering, LSTM

• Tools: Jupyter, GraphQL, Actian Data Connect

PROJECTS

Crime Data Analysis and Visualization

Python, SQL, Tableau, Pandas, NumPy, scikit-learn March 2025 – April 2025

• Cleaned and standardized over 1M LAPD crime records, enhancing dataset reliability by 25% through systematic preprocessing, including missing value treatment, duplicate removal, and data normalization.

• Designed and published dynamic Tableau dashboards and graphs, visualizing crime distribution across Los Angeles and highlighting key patterns through geospatial maps, time series trends, and categorical breakdowns. Natural Language Processing (NLP) for SQL Query Conversion using Deep Learning Python, LSTM, SQL, Dash Framework December 2020 – May 2021

• Designed and implemented a system to convert natural language queries into executable SQL queries, improving query comprehension and execution efficiency for non-technical users.

• Leveraged LSTM (Long Short-Term Memory) models to support the generation of basic SQL queries, including relational operators, GROUP BY, WHERE clauses, aggregate functions, DISTINCT clauses, and COUNT operations, achieving a 75% increase in query accuracy and streamlined data retrieval.

Customer Segmentation

Python, Dash Framework, Data Analysis, Machine Learning, scikit-learn June 2020 – November 2020

• Executed Customer Segmentation: To identify key insights that can boost sales by 50%, market basket analysis and K-Means Clustering techniques were employed to create consumer segmentation.

• In-Depth Data Analysis: Utilized machine learning algorithms to perform comprehensive data analysis on an online retail dataset, revealing significant patterns and behavioral trends within the data. CERTIFICATIONS & RECOGNITION

• Microsoft Certified: Azure Fundamentals (by Microsoft)

Contact this candidate