Rajat Dhawale

Assisted in developing and maintaining data processing pipelines using Python and PySpark for batch and near-real-time ingestion across various data layers.

• Supported in creating reliable data workflows on AWS services, including S3, Lambda, Glue, and Step Functions, for consistent data processing.
• Contributed to the design and optimisation of Snowflake-based data platforms for structured data transformation.
• Helped orchestrate workflows using Apache Airflow, enabling scheduling and automated data processing pipelines.
• Conducted data validation and quality checks to ensure accurate analytical outputs.
• Participated in supporting the development of data models for downstream analytics and reporting.
• Aided in optimising performance through efficient query design and improved data processing strategies.
• Worked with cross-functional teams to support data-driven decision-making.
• Maintained documentation and runbooks to support pipeline reliability and issue resolution.

Assisted in building and maintaining Python-based data processing pipelines for ingesting, cleansing, and transforming healthcare datasets for search and analytical applications.

• Supported the design and implementation of data transformation workflows to structure raw data into analysis-ready formats across multiple stages.
• Helped create structured datasets to enable search functionality and facilitate downstream analytics use cases.
• Participated in data migrations across PostgreSQL and MySQL, including schema mapping and data reconciliation.
• Conducted data validation and quality checks to ensure reliable outputs.
• Collaborated with team members and provided guidance to junior developers on Python development and data processing practices.
• Maintained automation of data workflows using Python and scripting, with version-controlled processes.

Role: Backend Python Developer.|Applied machine learning.

• Built Python-based backend pipelines to collect, clean, and store finance-related data from multiple web sources.
• Implemented web scraping and automation using Scrapy, BeautifulSoup, Requests, and Selenium, handling background jobs, CAPTCHA challenges, and IP blocking scenarios.
• Stored and managed processed data in PostgreSQL for analytics and model consumption.
• Used AWS services (S3, Lambda, EC2) to support data storage, scheduled processing, and backend workflows.
• Developed machine learning models using Python for business use cases: classification to categorise financial records (e.g. transaction type, risk category, and regression to predict numeric outcomes (e.g. amounts, trends, or scores.
• Performed feature engineering, train/test splits, and model evaluation using standard Python ML libraries.
• Automated jobs and model runs using Jenkins CI/CD and Python scripts.

Technologies: Python, AWS (S3, Lambda, EC2), PostgreSQL, Jenkins, Scrapy, Selenium, and Machine Learning (Classification, Regression).

• Built a customer targeting and retention system to boost sales using Python and Pandas for data analysis, summarisation, and visualisation.
• Performed customer segmentation and behaviour analysis to identify high-potential customers and assign incremental sales targets.
• Developed machine learning models for customer retention and propensity prediction, identifying customers likely to churn or to upsell.
• Applied classification techniques to predict customer retention probability, and regression models to estimate expected purchase value.
• Implemented feature engineering on customer demographics, purchase history, and engagement metrics.
• Built a Django-based web application with a simple HTML/JavaScript UI to display customer insights, and model outputs.
• Used SQL databases for storing customer data, model features, and prediction results.

Technologies: Python, Pandas, Machine Learning (Classification, Regression), SQL, Django, HTML, JavaScript, and Data Analysis.