Bhavya Shah
About Me
A highly skilled Data Professional with over 4 years of experience in Data Analytics, Data Engineering, and Data Science, complemented by a Master’s degree in Web and Data Science.
Expertise Includes:
- Designing data infrastructures and optimizing data pipelines.
- Implementing Machine Learning models, Natural Language Processing, and Generative AI solutions.
- Leveraging cloud platforms such as Amazon Web Services (AWS) and Microsoft Azure for deploying enterprise level solutions.
Passionate about delivering actionable insights and driving informed decision-making through innovative, data-driven solutions to tackle real-world challenges.
Education
- M.Sc. Web and Data Science | University of Koblenz, Germany (October 2021 – September 2024)
Grade: 2.4- Master Thesis: Detecting Mental Distress using Large Language Models, achieving 95% classification accuracy with fine-tuned MentalBERT and LLaMA-7B models.
- B.E. Information Technology | University of Mumbai, India (September 2020)
Grade: 1.8
Work Experience
Data Engineer | MEBEDO GmbH, Germany (July 2022 – June 2024)
- Architected and optimized ETL/ELT pipelines with Python, AWS, Spark, Kafka, and Airflow, achieving a 25% reduction in data processing latency to support high-volume data solutions.
- Analyzed and transformed large, complex datasets using SQL and dbt, then created Power BI dashboards to enable data-driven decision-making across teams.
- Designed and interpreted A/B tests to inform product strategies. Collaborated with cross-functional teams to align data solutions with business objectives in a fast-paced environment.
ML Researcher | University of Koblenz, Germany (October 2022 – May 2023)
- Developed Python-based ML and Neural Network models for COVID-19 strategies, improving predictive accuracy for public health measures.
- Employed NLP tools to streamline policymaking processes, reducing data processing time by 30%.
- Designed visualizations with Tableau to enhance decision-making and support cross-functional collaboration.
Data Analyst | dB SYS Online, India (October 2019 – September 2021)
- Processed and managed datasets of 100K+ records weekly using Python and SQL, improving data retrieval efficiency and accuracy of sales trend forecasts.
- Built interactive dashboards with Power BI, enabling stakeholders to make data-driven decisions that boosted business outcomes.
- Resolved data quality issues, ensuring accuracy and reliability, enhancing data consistency for key reports.
Projects
Advanced Analytics and Predictive Insights Platform
- Designed and implemented scalable ETL pipelines using Python, Apache Airflow, and AWS Glue, integrating multi-source data into AWS S3 and Redshift to enable real-time analytics and decision-making.
- Deployed predictive models in AWS SageMaker to identify telecom customer churn and applied ARIMA for sales forecasting, achieving a 20% reduction in churn and 30% fewer stock-outs.
- Built interactive dashboards with AWS Quicksight and implemented robust monitoring using AWS CloudWatch and CloudTrail, ensuring high data quality and actionable real-time insights for stakeholders.
AI-Powered Task Automation Agent
- Developed an AI-powered assistant using LangChain and Qwen-14B, automating tasks like email summarization, meeting scheduling, and contextual reminders.
- Integrated APIs such as Notion, Gmail, and Google Calendar, streamlining workflows and automating 80% of repetitive tasks to enhance user productivity.
- Delivered a seamless conversational interface using Gradio, improving task completion efficiency and user satisfaction through intuitive natural language interaction.
Technical Skills:
Languages & Tools: Python, SQL, NoSQL, AWS (S3, Lambda, Glue, Athena, RDS, Redshift, EC2, EMR, Quicksight, SageMaker, Kenisis, CloudTrail, CloudWatch), Ms Azure, Power BI, Tableau, Apache Spark, Kafka, Airflow, Databricks, Docker, Terraform, Ms SQL Server, MySQL, MongoDB, GitHub, GitLab, CI/CD, Jira, Confluence, PyCharm, Linux.
Certifications
- AWS Certified Machine Learning Engineer – Associate
- AWS Certified Data Engineer – Associate
- Machine Learning for Business Professionals
- Programming for Everybody