Eshwar Vattam Email & Phone Number

San Jose, Ca, Us

Brentford, Middlesex, Gb

• Conducted ad-hoc data analysis for regulatory submissions, reducing approval process time by 15%.• Analyzed pharmaceutical data from clinical trials on biochemical compounds using Python, identifying abnormalities through Power BI reporting to enhance data-driven decision-making and ensure compliance with regulatory standards. • Collaborated with teams to uncover trends and correlations in experimental datasets, enabling faster, data-driven decisions.• Optimized and streamlined data ingestion and cleaning pipelines using Python and Azure Data Factory, reducing processing time by 30% while ensuring data accuracy.• Automated data analysis workflows for regulatory submissions, reducing processing time by 15% and ensuring compliance accuracy.• Designed and implemented scalable data architectures using Azure Data Lake and Azure Synapse, ensuring robust data governance practices for compliance, security, and data quality across cloud environments.• Automated and implemented robust data validation protocols for pharmaceutical research, improving compliance by 20% and enhancing regulatory submission accuracy.• Applied advanced statistical models to forecast experimental outcomes and assess clinical trial efficacy, achieving high predictive accuracy and accelerating drug approval timelines.• Developed Python-based analytics pipelines for biochemical data, integrating Power BI dashboards to identify and visualize abnormalities in experimental datasets.• Built scalable analytics solutions using Databricks, processing large datasets and integrating insights into Power BI to support stakeholder decision-making.• Applied machine learning algorithms within Azure Databricks for predicting adverse drug reactions and treatment outcomes, deploying models and conducting model evaluation (hyperparameter tuning, A/B testing) to improve prediction accuracy by 20%.

Bangalore, Karnataka, In

• Developed and tested ETL mappings, workflows, and worklets using Informatica PowerCenter, achieving a 25% increase in data processing efficiency.• Designed and managed ETL pipelines using Azure Data Factory and AWS Glue, streamlining data integration and improving processing efficiency. • Implemented scalable data processing pipelines using Apache Kafka and Spark Streaming, improving processing speed by 25% and reducing latency for high-frequency data.• Optimized data models and queries, reducing resource utilization by 20% and enabling faster data access for end-users. • Implemented cloud-based solutions across projects using AWS (EC2, S3, Lambda, Redshift) and Azure (Virtual Machines, Blob Storage, Functions, Synapse Analytics), leveraging each platform's capabilities to deliver scalable storage, compute, and analytics solutions, enhancing performance and operational efficiency. • Exhibited proficiency in PySpark for large-scale data processing, enhancing analysis and script efficiency using Python. • Scaled the AutoML platform for big data support using Spark and Airflow, automating data flows and reducing training time for large datasets by 30%.• Built an end-to-end AutoML-based SaaS platform, Mateverse, by developing feature engineering, regression, and time-series training modules using Python, Flask, and Go, widely used across various industries. • Applied machine learning algorithms (decision trees, regression) for identifying patterns in research and supply chain optimization, with explainable AI dashboards to support stakeholder decisions.• Managed CI/CD pipelines with Azure DevOps, automating software development processes for seamless integration, testing, and deployment.