Harshitha Thodathara
Summary
Results-driven Software Engineer with expertise in Python, data analysis, and machine learning. Developed automation solutions reducing workloads by 60%, and implemented data pipelines achieving over 95% success.
Overview
3
3
years of professional experience
1
1
Certification
Work History
Software Engineer
CGI
01.2025 - 06.2025
- Developed automation for converting BIM Prolog to SWI-Prolog using Python on Azure VMs, reducing manual workload by 60%.
- Created data pipelines with ADF, SQL DB, Databricks, and Azure Storage, achieving over 95% data flow success.
- Optimized Snowflake objects including tables, views, procedures, and functions to enhance query performance.
- Built Power BI dashboards and Excel models to support RFPs and client proposals.
- Delivered interactive dashboards that provided key insights for strategic decision-making.
Research Assistant
Amrita Vishwa Vidyapeetham University
02.2024 - 12.2024
- Published three research papers in IEEE and Springer focused on healthcare security, traffic optimization, and medical machine learning applications using Python.
- Developed and deployed a speech-based machine learning model for Parkinson’s diagnosis, achieving 95% accuracy with Random Forest and XGBoost.
- Processed over 50,000 medical records using PySpark and SQL, enhancing model performance by 12% through effective feature engineering.
- Implemented secure data handling protocols and cryptographic measures to protect healthcare information, adhering to industry best practices.
- Collaborated with research teams utilizing Git for code management, conducting thorough code reviews, and participating in peer review for academic publications.
Machine Learning Engineer
Cybrowse Digital Pvt Ltd
01.2023 - 06.2023
- Engineered credit risk machine learning models with SQL, PL/SQL, and Python, analyzing 50K+ records and achieving a 25% reduction in analysis time through query optimization.
- Established comprehensive data cleaning workflows using Pandas and NumPy, improving model reliability by effectively managing missing values.
- Designed and implemented automated Excel dashboards with Python pipelines, monitoring 15 KPIs for portfolio performance across three teams.
- Collaborated on code reviews while applying Git for version control to ensure secure, maintainable software solutions.
Data Analyst
M3 Solutions
02.2022 - 07.2022
- Engineered secure data pipelines for 350K+ patient records using PySpark, Python, and SQL.
Implemented data governance protocols, enhancing data quality by 15% through systematic validation. - Designed automated monitoring systems for 12 KPIs with Python and statistical analysis techniques.
- Reduced data errors by 18% through technical troubleshooting and quality assurance frameworks.
- Applied modern software development practices, including Git version control and collaborative code reviews.
- Utilized Agile methodologies for healthcare data modeling and reporting solutions.
- Optimized databases through SQL query tuning and indexing strategies, ensuring efficient operations.
- Improved system performance through strategic database optimization initiatives.
Education
Bachelor of Science - Computer Science
Amrita Vishwa Vidyapeetham University
Skills
Programming languages: Python, SQL, Shell scripting
Big data technologies: PySpark, Spark, Kafka, SnowSQL
Database management: MySQL, SQL Server, PostgreSQL, Snowflake, MongoDB
Workflow orchestration: Airflow
Machine learning techniques: Supervised learning, KNNs, Random forests, XGBoost, Linear regression, Decision trees
Cloud services:
AWS: Lambda, AWS Glue, Athena, Redshift, EMR, EC2, S3
Azure: Azure Data Factory, Databricks, Blob storage, Azure Data Lake
GCP: Composer, BigQuery, Cloud Storage (GCS), Spanner, Dataflow, Dataproc
Development environments: Databricks, Visual Studio Code, PyCharm, DBT, Anaconda, IntelliJ
Data visualization tools: Tableau, Power BI
Python libraries: NumPy, Pandas, Matplotlib, BeautifulSoup, Scikit-learn
Certification
- Databricks Data Engineer Associate
- Snowflake SnowPro Core
- Microsoft Certified : Azure Fundamentals
- Microsoft Certified : Azure Data Fundamentals
Timeline
Software Engineer
CGI
01.2025 - 06.2025
Research Assistant
Amrita Vishwa Vidyapeetham University
02.2024 - 12.2024
Machine Learning Engineer
Cybrowse Digital Pvt Ltd
01.2023 - 06.2023
Data Analyst
M3 Solutions
02.2022 - 07.2022
Bachelor of Science - Computer Science
Amrita Vishwa Vidyapeetham University